US20020128818A1 - Method and system to answer a natural-language question - Google Patents
Method and system to answer a natural-language question Download PDFInfo
- Publication number
- US20020128818A1 US20020128818A1 US10/060,120 US6012002A US2002128818A1 US 20020128818 A1 US20020128818 A1 US 20020128818A1 US 6012002 A US6012002 A US 6012002A US 2002128818 A1 US2002128818 A1 US 2002128818A1
- Authority
- US
- United States
- Prior art keywords
- question
- user
- phrase
- database
- formats
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
- G09B7/04—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S706/00—Data processing: artificial intelligence
- Y10S706/902—Application using ai with detail of the ai system
- Y10S706/927—Education or instruction
Definitions
- the present invention relates generally to methods and systems to answer a question, and more particularly to methods and systems to accurately answer a natural-language question.
- the present invention provides methods and systems that can quickly provide a handful of accurate responses to a natural-language question.
- the responses can depend on additional information about the user and about the subject matter of the question so as to significantly improve on the relevancy of the responses.
- the user is allowed to pick one or more of the responses to have an answer generated.
- the answer to the question can be in a language different from the language of the question to provide more relevant answers.
- One embodiment of the present invention includes a system with an input device, an answer generator and an output device.
- the answer generator having access to a database of phrases and question formats, identifies at least one phrase in the question to generate phrased questions. This identification process uses phrases in the database and at least one grammatical rule.
- the identified phrase can then be linked to at least one category based on, for example, one semantic rule. Then the system provides a score to the categorized phrase. This score can depend on a piece of information about the user and/or about the subject matter of the question. In one embodiment, this piece of information is different from the fact that the user has asked the question.
- the piece of information can be related to the user's response to an inquiry from the system.
- the system can ask the user to specify the subject matter of the question. Assume that the user asks the following question: “In the eighteenth century, what did Indians typically eat?” The system can ask the user if the subject matter of the question is related to India or the aboriginal peoples of North America. Based on the user's response, the system can provide a more relevant response to the user.
- the piece of information is related to an interest of the user. Again, if the user is interested in traveling, and not food, certain ambiguities in his question can be resolved. Based on the user's response to certain inquiries from the system, the accuracy of the answer can be enhanced.
- the piece of information about the user is related to a question previously asked by the user. For example, if the user has been asking questions on sports, probably the word, ball, in his question is not related to ball bearings, which are mechanical parts.
- the score of the categorized phrase can change. In another embodiment, based on information of the subject matter the question is in, the score of the categorized phrase can change.
- the system can identify at least two question formats in the database based on the score. These question formats can again help the system resolve ambiguities in the question. For example, the question is, “How to play bridge?” Assume that the question is in the general subject area of card games. It is not clear if the user wants to find out basic rules on the card game bridge or to learn some more advanced techniques. Then, one question format can be on basic rules on bridge, and the other format can be on bridge techniques. The user is allowed to pick at least one of the question formats to have the corresponding answer generated.
- the answer can be in a language different from the language of the question. This improves on the accuracy of the answers to the question. For example, if the user is interested in Japan, and if the user understands Japanese, based on the question format picked, a Japanese answer is identified to his English question. Such answers can provide more relevant information to the user.
- FIG. 1 shows one embodiment of the invention.
- FIG. 2 shows one embodiment of an answer generator of the invention.
- FIG. 3 shows one set of steps implemented by one embodiment of an answer generator of the invention.
- FIGS. 4 A-B show embodiments implementing the invention.
- FIG. 5 shows examples of ways to regularize the question in the invention.
- FIG. 6 shows one set of steps related to identifying phrases in the question of the invention.
- FIG. 7 shows one set of steps related to identifying question structures in the invention.
- FIG. 8 shows examples of factors affecting scores in the invention.
- FIG. 9 shows one set of steps related to identifying question formats in the invention.
- FIG. 10 shows one set of steps related to identifying answer in the invention.
- FIGS. 1 - 10 Same numerals in FIGS. 1 - 10 are assigned to similar elements in all the figures. Embodiments of the invention are discussed below with reference to FIGS. 1 - 10 . However, those skilled in the art will readily appreciate that the detailed description given herein with respect to these figures is for explanatory purposes as the invention extends beyond these limited embodiments.
- FIG. 1 shows one embodiment of a system 50 of the present invention. It includes an input device 52 coupled to an answer generator 54 , which is coupled to an output device 56 .
- FIG. 2 shows one embodiment of the answer generator 54 implementing a set 120 of steps shown in FIG. 3.
- a user enters a question into the input device 52 , such as a keyboard, a mouse or a voice recognition system.
- the question or a representation of the question can be transmitted by the input device to the answer generator 54 .
- the answer generator 54 includes a number of elements.
- the answer generator 54 can include a question regularizer 80 , a phrase identifier 82 , a question structure identifier 84 , a question format identifier 86 and an answer identifier 88 .
- the question regularizer 80 regularizes (step 122 ) words in the question, such as by replacing words with their roots; the phrase identifier 82 identifies (step 124 ) phrases in the regularized question to generate phrased questions; the question structure identifier 84 generates (step 126 ) question structures from the phrased question; based on the question structures, the question format identifier 86 identifies (step 128 ) and retrieves one or more question formats, which the user is allowed to pick from; and then the answer identifier 88 identifies (step 132 ) ad retrieves one or more answers for the question. Note that the answer identifier 88 can access the Internet or the Web for answers.
- the generator 54 can also include a database 90 of relevant information to be accessed by different elements of the generator 54 .
- the database 90 can be a relational database, an object database or other forms of database.
- the output device 56 such as a monitor, a printer or a voice synthesizer, can present the answer to the user.
- FIG. 4A shows one physical embodiment 150 implementing one embodiment of the invention, preferably in software and hardware.
- the embodiment 150 includes a server computer 152 and a number of client computers, such as 154 , which can be a personal computer.
- Each client computer communicates to the server computer 152 through a dedicated communication link, or a computer network 156 .
- the link can be the Internet, intranet or other types of private-public networks.
- FIG. 4B shows one embodiment of a client computer 154 . It typically includes a bus 159 connecting a number of components, such as a processing unit 160 , a main memory 162 , an I/O controller 164 , a peripheral controller 166 , a graphics adapter 168 , a circuit board 180 and a network interface adapter 170 .
- the I/O controller 164 is connected to components, such as a harddisk drive 172 and a floppy disk drive 174 .
- the peripheral controller 166 can be connected to one or more peripheral components, such as a keyboard 176 and a mouse 182 .
- the graphics adapter 168 can be connected to a monitor 178 .
- the circuit board 180 can be coupled to audio signals 181 ; and the network interface adapter 170 can be connected to a network 120 , which can be the Internet, an intranet, the Web or other forms of networks.
- the processing unit 160 can be an application specific chip.
- the input device 52 and the output device 56 may be in a client computer; and the answer generator 54 may reside in a server computer.
- the input device 52 , the output device 56 , the answer generator 54 other than the database 90 are in a client computer; and the database 90 is in a server computer.
- the database 90 can reside in a storage medium in a client computer, or with part of it in the client computer and another part in the server computer.
- the system 50 is in a client computer.
- the input device 52 and the output device 56 are in a client computer; the answer generator 54 other than the database 90 is in a middleware apparatus, such as a Web server; and the database 90 with its management system are in a back-end server, which can be a database server. Note that different elements of the answer generator 54 can also reside in different components.
- the question can be on a subject, which can be broad or narrow.
- the subject can cover mathematics or history, or it can cover the JAVA programming language.
- the subject covers information in a car, such as a Toyota Camry, and the user wants to understand this merchandise before buying it.
- the subject covers the real estate market in a certain geographical area, and again the user wants to understand the market before buying a house.
- a question can be defined as an inquiry demanding an answer; and an answer can be defined as a statement satisfying the inquiry.
- the question can be a natural-language question, which is a question used in our everyday language.
- a natural-language question can be in English or other languages, such as French. Examples of natural-language questions are:
- one grammatical rule is that a question is made of phrases; another grammatical rule is that every phrase is made of one or more words.
- Such rules can define a grammatical structure.
- a question formed under such rules is grammatically context-free, and the question is in a context-free grammatical structure.
- FIG. 5 shows examples of ways to regularize the question.
- the question regularizer 80 regularizes words in the question, for example, by replacing certain words in the question with their roots.
- One objective of the regularizer is to reduce the size of the database 90 and the amount of computation required to analyze the question.
- the regularizer 80 identifies every word in the question. Then it replaces words with their roots if they are not already in their root forms. For example, the regularizer changes verbs (step 202 ) of different forms in the question into their present tense, and nouns (step 204 ) into singular.
- Every word in the question can be hashed into a hash value.
- each character is represented by eight bits, such as by its corresponding eight-bit ASCII codes.
- the hashing function is performed by first pairing characters together in every word of the question. If a word has an odd number of characters, then the last character of the word is paired with zero. Each paired characters becomes a sixteen-bit number. Every word could have a number of sixteen-bit numbers. The character does not have to be represented by the eight-bit ASCII codes. In another embodiment, with each character represented by its sixteen-bit unicode, the characters are not aired. Again every word could have a number of sixteen-bit numbers.
- each hash value can be used to represent two different words.
- One word can be in one language and the other in another language, with both languages represented by unicodes.
- a 16 Mbit memory could be used to hold different combinations of twenty-four bit hash values to represent different words. This approach should be applicable to most natural languages.
- commonly-used words have been previously hashed and stored in the database 90 .
- the hash values of words in the question are compared to hash values in the tables and may be replaced by root-forms hash values.
- the hash values of verbs of different forms in the question are mapped to and replaced by the hash values of their present tenses, and similarly, the hash values of plural nouns are mapped to and replaced by their corresponding singular form hash values.
- the phrase identifier 82 can identify phrases in the question.
- FIG. 6 shows one set 124 of steps related to identifying phrases. Note that the process of identifying does not have to include the process of understanding, determining its presence in the database, or extracting.
- the identifier identifies phrases from the beginning or the first word (step 252 ) of the question. It identifies the first word in the question, and then determines if the first word is in the database 90 . If it is, it will be classified as a phrase of the question. Then, the identifier identifies the first two words. If there is a corresponding term with such two words in the database 90 , then the two words are classified as another phrase of the question.
- the phrase determination process can again be done through a hashing function.
- One approach is to add the hash values of each of the words in a phrase. If the sum has more than 24 bits, throw away the carry. The remaining 24 bits would be the hash value of the phrase.
- the two words in the question can be hashed into a hash value, which is compared to hash values in the database 90 . If such a hash value exists in the database 90 , then the two words are classified as a phrase. In one embodiment, this process continues on up to the first twenty words in the question.
- the identifier stops adding another word to identify phrases in the question.
- a hash value that exists in the database 90 does not mean that its corresponding word or words can have independent meaning.
- the existence of a hash value in the database 90 can imply that the phrase identifier 82 should continue on adding words to look for phrases.
- the identifier 82 should continue on adding words to identify the longest matching phrase, which can be a phrase with six words.
- the term, “with respect” may not be a phrase, or does not have independent meaning. But the hash value of such a term can be in the database 90 .
- the identifier adds the next word in the question to determine if the three-word combination exists in the database 90 . If the third word is the word “to”, then the three-word combination is a preposition with independent meaning, and can have a hash value in the database 90 .
- the identifier After identifying all of the phrases from the first word, the identifier starts from identifying (step 254 ) phrases from the second word of the question, and performs similar identification process as it has done from the first word. One difference is that the starting point of the analysis is the second word.
- the question is, “Are ball bearings round?”
- the identifier starts from the word, “are”, and stops after the word, “balls”, because there is no hash value for the term, “are ball”. Then, the identifier starts from the word, “ball”, and finds a hash value. This suggests that the identifier should continue on, and found the hash value for the term, “ball bearings”.
- the identifier can continue on identifying phrases from the remaining words (step 256 ) in the question.
- the starting point of the analysis moves from one word to the next, down the question, until all of the words in the sentence have been exhausted.
- the identifier should have identified all of the phrases in the question with corresponding phrases in the database 90 .
- the identifier then removes (step 258 ) words in the question that are not in any identified phrases. For example, there is a word, “xyz”, in the sentence, which is not found in any of the identified phrases. That word will not be considered in subsequent analysis, or will be ignored. In essence, that word is removed from the question.
- the phrase identifier 82 From the identified phrases, the phrase identifier 82 generates (step 260 ) a number of phrased questions. Each phrased question is a combination of one or more identified phrases that match the question. All of the phrased questions cover different combinations of the identified phrases that match the question.
- the question is “Cash cow?”
- the first phrased question has two phrases, each with one word.
- the second phrased question has only one phrase, with two words.
- the question structure identifier 84 identifies one or more question structures.
- FIG. 7 shows one set 126 of steps related to identifying question structures.
- phrases in the database 90 are categorized (step 302 ).
- a phrase can belong to one or more categories.
- a category can be a group of phrases, with one or more common characteristics, which can be related to a subject matter. For example, there are two categories and they are Congress and finance. Then, one semantic rule can be that the phrase “bill” belongs to both categories, while another semantic rule can be that the phrase “Capital Asset Pricing Model” belongs to the category of finance.
- each of its phrases can be linked (step 302 ) by a linker to one or more categories.
- a linker for example, for the phrased question, “cash” “cow”, the phrase “cash” can be linked to the categories of finance, banking and payment; and the phrase “cow” can be linked to the categories of animals and diary products.
- the phrased question “cash cow”, the phrase “cash cow” can be linked to the categories of finance and banking.
- Each category can be given a score.
- the score denotes the importance of the category, or the relevancy of the category to the question.
- the score can depend on the meaning of the category. For example, the category of Congress is given 10 points, and the category of finance is given 30 terms because more people ask about finance than Congress.
- the scores can depend on the subject the user is asking. For example, if the question is about travel, the category on city can be given 20 points, and the category on animal 5 points. Scoring categories can be done dynamically. For example, after the question has been determined to be in the area of finance, the category on insect can be dynamically given 0.1 point or even 0 points, while the category on investment can be given 100 points. In this example, one semantic rule can be that in the finance area, the score of the category of investment is higher than that of the category of insect.
- the scores given to interrogative pronouns can depend on the type of questions asked. In the travel domain or in questions on traveling, the categories for “how”, “where”, “what” and “when” can be given higher scores than the category for “who”.
- Each phrase in a phrased question can belong to more than one categories. With the categories having scores, each phrase belonging to multiple categories can have more than one scores. In one embodiment, the category with the highest score is selected to be the category of that phrase, or to be the score of that categorized phrase (step 304 ).
- the score of at least one phrase depends on information about the user. This information can be specific to that user. FIG. 8 shows examples of factors affecting the scores. In one embodiment, the information about the user is more than the fact that the user just asked the system 50 a question.
- the information can be related to the question's subject matter 350 , identified by the user.
- the system 50 can ask the user the subject of his question.
- the user has to select one subject of interest. All of his question would be considered to be related to that subject.
- the information can be related to the user's previous question 352 .
- the user has been asking questions related to health, and his question has the word, virus, in it.
- the system 50 would not consider the question to be related to computer virus, but would focus on the type of virus affecting our health.
- the input and output devices are in a client computer used by the user to ask questions
- the answer generator is in a server computer.
- the Web browser in the client computer stores the question asked by the user in cookies.
- the cookies are sent back to the server computer.
- the responses generated by the server computer depend on information in the cookies, such as the one or more questions previously asked by the user.
- previous questions can be stored in, for example, HTML forms, which support hidden variables, or HTML scripts written in JavaScript, which supports variables.
- the question format identifier can generate a set of instructions to represent question formats to be sent to the user. The instructions can be written in HTML form.
- the input device remembers the one or more question asked by the user and the question formats selected by the user. After a user has selected a question format or asked a new question, the input device can send it to the answer generator.
- the format sent can also include one or more previous questions asked by the user during the same session. Those questions are stored in the hidden variables of the question format.
- all of the user's inputs can be stored. Whenever anything is sent to the answer generator, all of the user's previous inputs can be sent to the generator in the hidden variables.
- the information can be related to a profile of the user 354 .
- the user is asked to fill in a questionnaire about himself before he starts asking question.
- His profile can include his language skill, 356 , such as the languages he prefers his answer to be in; his areas of interest, 358 , such as the types of songs he likes; and his ethnic background, 360 .
- the user is an Egyptian.
- categories related to Egypt can be given higher scores.
- Such information would help the system 50 tailor more accurate and relevant responses to him.
- a user enters his identifier when he starts to use the system. Then, next time when he uses the system 50 , based on his identification, the system 50 can retrieve his profile. His profile can be updated based on his usage of the system 50 , for example, based on questions he just asked. Again, his identification can be stored in cookies.
- certain information 357 in the user's profile does not have to be directly entered by the user.
- the invention can be implemented in a client-server environment, with the client having an IP address. At least a portion of the answer generator resides in a server, and at least a portion of the input device in a client. Certain information in the user's profile may depend on the IP address 359 .
- the client After the client has established, for example, a HTTP session with the server, the client's IP address would be passed to the server. Based on the source IP address, the server can go to a domain name database, such as those hosted by Network Solution Incorporated, to access the domain name of the client.
- the domain name gives a number of information, such as the point of presence of the Internet service provider used by the client.
- the server would then be aware, for example, the approximate ZIP code of the client, or the approximate geographical location of the client. As an example, such information can be used in the following way. If the user is approximately located in San Francisco, and he is asking for hotel information in Boston, the server can assume that the user intends to travel to Boston. Based on such an assumption, the server can send to the client answers related to car rental information and flight ticket information when responding to his question for hotel information.
- the system 50 can ask the user to refine the question.
- the question includes the word “current”.
- the system 50 can ask the user if his question is related to the subject of electricity or time or other physical phenomena.
- information related to the user's question can be acquired to improve on the responses to the question.
- the system can ask the user more than one question so as to refine the answer. For example, after the user has responded that the word “current” is related to other physical phenomena, the system 50 can ask the user if the question is related to wind or ocean or other physical phenomena so as to better understand the question.
- the score of at least one phrase depends on the subject matter of the question.
- Information on the subject matter of the question, or the domain knowledge does not have to be from the user.
- the system 50 can be tailored for a specific subject, such as information related to a specific company, including that company's products. That system can be designed to answer questions related to the company, with many phrases, question formats and answer formats focused on the company.
- the company is a hardware company, and the user asks the question, “Do you have nails?”
- the system 50 would not interpret the question to refer to nails as in finger nails.
- the system 50 assumes the question to be related to nails, as in screws and nails, and responds accordingly.
- the system is tailored to more than one subject matter, and can be switched from one subject matter to another using the same database. The switch can be done, for example, by adjusting the scores of different categories based on their relevancy to the subject matter.
- scores on categories and, in turn, phrases can be changed.
- the change can be dynamic. In other words, scores are modified as the system gains more information. This can be done, for example, by applying multipliers to scores of categories to be changed.
- scores are changed according to the information related to the user and/or the subject matter of the question.
- due to changes in the scores of the categories a phrase previously linked to a category is modified to be linked to another category.
- the structure identifier after categorizing and scoring each phrase in a phrased question, the structure identifier generates (step 306 ) a number of question structures.
- Each phrase in the question can be linked to a category, and each phrased question can be represented by the corresponding categories.
- the categorized representation of each phrase question can be known as a question structure, or a question structure can be a list of categories.
- the question structure of the phrase question, “cash” “cow” can be “finance” “animals”
- the question structure of the phrase question “cash cow” can be “finance”.
- the question, “Cash cow?” is linked to two question structures.
- the number of question structures generated can be reduced, which could increase the speed to generate a response, and could also reduce ambiguity in the question.
- the method is by reducing the number of categories.
- One way is to form categories of categories, or a hierarchy of categories. Each category can be given a name. With each question structure being a list of categories, each question structure can be represented by a list of category names.
- the phrase identifier 82 can operate on the list of category names to determine category-of-categories.
- the category-of-category approach can be explained by the following example.
- the original question includes the phrase, “San Jose of California”. “San Jose” is under the category of city, “of” is under the category of “preposition”, and “California” is under the category of State.
- One semantic rule may be that there is a “City of State” category to replace the list of categories “city” “preposition” “State”.
- This type of category-of-categories analysis can be extended into a category hierarchy.
- the “city”, “preposition” and “State” can be considered as first level categories, while the “city of State” category can be considered as a second level category.
- the method to identify higher level categories can be the same as the method to identify second level categories based on first level categories, as long as each category is given a name.
- a third level category can replace a list of second level categories.
- one semantic rule is that a higher level category is assigned a higher score than its lower level categories.
- the “city of State” category has a higher score than the “city”, “preposition” and “State” categories.
- the question structure identifier 84 can select a number of the generated question structures.
- the structure identifier provides (step 308 ) a score to each question structure by summing the scores of all of its categories.
- the question structure identifier 84 selects (step 310 ), for example, the question structure with the highest score to be the question structures representing the question. In one example, the identifier selects the structures with the top five highest scores to be the structures representing the question.
- the question format identifier 86 identifies one or more question formats in the database 90 .
- FIG. 9 shows one set of steps related to identifying question formats.
- Each question format can be a pre-defined question with one or more phrases and one or more categories.
- the following can be a question format:
- Each category in a question format has a number of corresponding phrases.
- the corresponding phrases of the category “major city” can include all of the cities in the United States with population exceeding one million people.
- the question formats can be pre-defined and stored in the database 90 .
- One way to generate them can be based on commonly-asked questions. For example, if more than twenty people ask the same or substantially similar question when they use the system 50 , a system administrator can generate a question format for that question structure. To illustrate, more than twenty people asked the following questions, or a variation of the following questions:
- a question structure can have one or more categories.
- the question format identifier identifies every question format that has all of the categories in that question structure (step 402 ). There can be situations when a question structure has a number of categories, and no question format in the database 90 has all of the categories.
- the question format identifier identifies question formats that have at least one category in the question structure.
- the question format identifier 86 can select (step 404 ) one or more of them.
- One selection criterion is based on scores of the question formats.
- Each question format includes one or more categories, and each category has a score. The sum of all of the scores of the categories in a question format gives the question format a score. In one embodiment, the question format with the highest score is selected. In another embodiment, the five question formats with the highest scores are selected.
- a category in a question format can have a default value.
- Each category typically has many phrases.
- one of the phrases is selected to be the default phrase (step 406 ) of the category in the question format. That phrase can be the corresponding phrase in the original question leading to the selection of the category and the question format.
- the question is, “What is the temperature in San Francisco?”
- the question format selected is, “What is the temperature in ‘city’?”
- the question format becomes, “What is the temperature in ‘San Francisco’?” In other words, San Francisco has been chosen to be the default city.
- the system 50 allows (step 130 ) the user to pick one or more of the selected question formats. This can be done by the question format identifier generating a number of instructions representing the selected question formats, and sending the instructions to the output device 56 .
- the browser in the output device 56 based on the instructions, displays the selected question formats to allow the user to pick.
- the output device 56 can show the user all of the selected question formats. Next to each of the selected question formats there can be an enter icon. If the user clicks the enter icon, that question format would be picked as the selected one.
- the user can also choose any one of the phrases within each category of a question format. For example, the question format picked is, “What is the temperature in ‘San Francisco’?” And the user decides to find out the temperature in Los Angeles.
- the user can click the phrase “San Francisco”, then a list of cities shows up on the output device 56 . The user can scroll down the list to pick Los Angeles. Then, by clicking the enter icon next to the question, the user would have selected the question format, “What is the temperature in ‘Los Angeles’?”
- the answer identifier 88 identifies one or more answers for the user.
- FIG. 10 shows one set 132 of steps related to identifying answer.
- each question format has its corresponding answer format.
- the answer identifier 88 retrieves (step 452 ) one or more answer formats for each question format.
- the answer format can be an answer or can be an address of an answer. In situations where the answer format is an address of an answer, the answer identifier can also access (step 454 ) the answer based on the answer format.
- the answer format of a question format is the URL of a Web page. If the user picks that question format, the answer identifier 88 would retrieve the corresponding answer format, and fetch the one or more Web pages with the retrieved URL.
- a set of instructions are generated to search for information, for example, from different databases or other sources, such as the Web.
- the instructions can be queries written, for example, in SQL, or HTTP.
- the output device 56 also shows the answer to the question format with the highest score.
- the phrase identifier 82 can identify a few phrases, and then the question structure identifier 84 can generate a few question structures. As long as there are, for example, ten question structures with scores more than a threshold value, the system 50 would stop looking for additional question structures. If there are only nine such structures, the phrase identifier 82 would identify some more phrases, and the structure identifier 84 would generate more question structures. In other words, the system 50 does not have to look for all phrases in the question before question structures are identified.
- the threshold value can be set by experience. For example, from past usage, maximum scores of question structures in certain subject areas, such as the traveling domain, are typically less than eighty. Then, for those types of questions, the question structure identifier 84 could set the threshold value to be seventy five. This approach would speed up the time required to respond to the question.
- the question formats can be grouped together based on common characteristics. For example, all formats related to San Francisco are grouped together. Then based on information about the subject matter and/or the user, such as the user is asking questions about San Francisco, those formats would be selected to have one or more of them identified by the question format identifier 86 . In another embodiment, if the question is related to San Francisco, the scores of formats related to San Francisco would be multiplied by a factor of, for example, five. This could increase the chance of finding more relevant question formats for the user, and, in turn, more relevant answer to the question.
- the database can include information of different languages.
- the user can ask the question in English.
- the subsequent analysis can be in English, with, for example, the question formats also in English.
- each selected question format is transformed into instructions, with phrases or categories in the format translated into their equivalent terms in other languages. At least one of those categories can be selected in view of a phrase in the question.
- the translation can be done, for example, through unicodes. As an illustration, the English name of a person is translated into that person's name as known in his native language.
- the instructions can be used to search for or retrieve one or more answers to the question.
- a different embodiment is that the system administrator can previously define certain answer formats to be in French, or to be the URL of a French Web site for the answer. French information would be retrieved to be the answers.
- the regularizer 80 serves the function of a translator by translating the question into the other language. From that point onwards, the analysis will be in the other language. For example, the question is translated into German. Subsequently, phrases, structures, formats and answers would all be in German.
- One embodiment includes a computer readable media containing computer program code.
- the code when executed by a computer causes the computer to perform at least some of the steps of the present invention, such as some of those defined in FIG. 3.
- a signal is sent to a computer causing the computer to perform at least some of the steps of the present invention, such as some of those defined in FIG. 3.
- This signal can include the question, or a representation of the question, asked by the user.
- the computer can include or can gain access to the database 90 .
- steps shown in FIG. 3 or the answer generator shown in FIG. 2 can be implemented in hardware or in software or in firmware.
- the implementation process should be obvious to those skilled in the art.
Abstract
Description
- The present invention is a continuation-in-part of co-pending U.S. application entitled, “Learning Method and System Based on Questioning III”, filed on Jul. 2, 1999, invented by Chi Fai Ho and Peter Tong, and having a Ser. No. of 09/347,184, which is hereby incorporated by reference into this application.
- The present invention relates generally to methods and systems to answer a question, and more particularly to methods and systems to accurately answer a natural-language question.
- Numerous search engines in the market have provided us with an unprecedented amount of freely-available information. All we have to do is to type in our questions, and we will be inundated by information. For example, there is a search engine that regularly gives us tens of thousands of Web sites to a single question. It would take practically days to go through every single site to find our answer, especially if our network connections are through relatively low speed modems. We do not want thousands of answers to our questions. All we want is a handful of meaningful ones.
- Another challenge faced by users of many search engines is to search by key words. We have to extract key words from our questions, and then use them to ask our questions. We might also use enhanced features provided by search engines, such as + or − delimiters before the key words, to indicate our preferences. Unfortunately, this is unnatural. How often do we ask questions using key words? The better way is to ask with a natural language.
- There are natural-language search engines. Some of them also provide limited number of responses. However, their responses are inaccurate, and typically do not provide satisfactory answers to our questions. Their answers are not tailored to our needs.
- Providing accurate responses to natural language questions is a very difficult problem, especially when our questions are not definite. For example, if you ask the question, “Do you like Turkey?”, it is not clear if your question is about the country Turkey or the animal Turkey. Add to this challenge is the need to get answers quickly. Time is very valuable and we prefer not to wait for a long time to get our answers.
- To further complicate the problem is the need to get information from documents written in different languages. For example, if we want to learn about climbing Mount Fuji in Japan, probably most of the information is in Japanese. Many search engines in the United States only search for information in English, and ignore information in all other languages. The reason may be because translation errors would lead to even less accurate answers.
- It should be apparent from the foregoing that there is still a need for a natural-language question-answering system that can accurately and quickly answer our questions, without providing us with thousands of irrelevant choices. Furthermore, it is desirable for the system to provide us with information from different languages.
- The present invention provides methods and systems that can quickly provide a handful of accurate responses to a natural-language question. The responses can depend on additional information about the user and about the subject matter of the question so as to significantly improve on the relevancy of the responses. The user is allowed to pick one or more of the responses to have an answer generated. Furthermore, the answer to the question can be in a language different from the language of the question to provide more relevant answers.
- One embodiment of the present invention includes a system with an input device, an answer generator and an output device. The answer generator, having access to a database of phrases and question formats, identifies at least one phrase in the question to generate phrased questions. This identification process uses phrases in the database and at least one grammatical rule.
- The identified phrase can then be linked to at least one category based on, for example, one semantic rule. Then the system provides a score to the categorized phrase. This score can depend on a piece of information about the user and/or about the subject matter of the question. In one embodiment, this piece of information is different from the fact that the user has asked the question.
- The piece of information can be related to the user's response to an inquiry from the system. For example, the system can ask the user to specify the subject matter of the question. Assume that the user asks the following question: “In the eighteenth century, what did Indians typically eat?” The system can ask the user if the subject matter of the question is related to India or the aboriginal peoples of North America. Based on the user's response, the system can provide a more relevant response to the user.
- In another example, the piece of information is related to an interest of the user. Again, if the user is interested in traveling, and not food, certain ambiguities in his question can be resolved. Based on the user's response to certain inquiries from the system, the accuracy of the answer can be enhanced.
- In another embodiment, the piece of information about the user is related to a question previously asked by the user. For example, if the user has been asking questions on sports, probably the word, ball, in his question is not related to ball bearings, which are mechanical parts.
- Typically, the more information the system has on the user and the subject matter of the question, the more accurate is the answer to the user's question. The reason is similar to the situation of our responding to our friend's question before he even asks it. Sometimes we understand what they want to know through non-verbal communication or our previous interactions.
- Based on information on the user, the score of the categorized phrase can change. In another embodiment, based on information of the subject matter the question is in, the score of the categorized phrase can change.
- After providing the score to the categorized phrase, the system can identify at least two question formats in the database based on the score. These question formats can again help the system resolve ambiguities in the question. For example, the question is, “How to play bridge?” Assume that the question is in the general subject area of card games. It is not clear if the user wants to find out basic rules on the card game bridge or to learn some more advanced techniques. Then, one question format can be on basic rules on bridge, and the other format can be on bridge techniques. The user is allowed to pick at least one of the question formats to have the corresponding answer generated.
- In another embodiment, the answer can be in a language different from the language of the question. This improves on the accuracy of the answers to the question. For example, if the user is interested in Japan, and if the user understands Japanese, based on the question format picked, a Japanese answer is identified to his English question. Such answers can provide more relevant information to the user.
- Other aspects and advantages of the present invention will become apparent from the following detailed description, which, when taken in conjunction with the accompanying drawings, illustrates by way of example the principles of the invention.
- FIG. 1 shows one embodiment of the invention.
- FIG. 2 shows one embodiment of an answer generator of the invention.
- FIG. 3 shows one set of steps implemented by one embodiment of an answer generator of the invention.
- FIGS.4A-B show embodiments implementing the invention.
- FIG. 5 shows examples of ways to regularize the question in the invention.
- FIG. 6 shows one set of steps related to identifying phrases in the question of the invention.
- FIG. 7 shows one set of steps related to identifying question structures in the invention.
- FIG. 8 shows examples of factors affecting scores in the invention.
- FIG. 9 shows one set of steps related to identifying question formats in the invention.
- FIG. 10 shows one set of steps related to identifying answer in the invention.
- Same numerals in FIGS.1-10 are assigned to similar elements in all the figures. Embodiments of the invention are discussed below with reference to FIGS. 1-10. However, those skilled in the art will readily appreciate that the detailed description given herein with respect to these figures is for explanatory purposes as the invention extends beyond these limited embodiments.
- FIG. 1 shows one embodiment of a
system 50 of the present invention. It includes aninput device 52 coupled to ananswer generator 54, which is coupled to anoutput device 56. FIG. 2 shows one embodiment of theanswer generator 54 implementing aset 120 of steps shown in FIG. 3. - A user enters a question into the
input device 52, such as a keyboard, a mouse or a voice recognition system. The question or a representation of the question can be transmitted by the input device to theanswer generator 54. - In one embodiment, the
answer generator 54 includes a number of elements. Theanswer generator 54 can include aquestion regularizer 80, aphrase identifier 82, aquestion structure identifier 84, aquestion format identifier 86 and ananswer identifier 88. In general terms, thequestion regularizer 80 regularizes (step 122) words in the question, such as by replacing words with their roots; thephrase identifier 82 identifies (step 124) phrases in the regularized question to generate phrased questions; thequestion structure identifier 84 generates (step 126) question structures from the phrased question; based on the question structures, thequestion format identifier 86 identifies (step 128) and retrieves one or more question formats, which the user is allowed to pick from; and then theanswer identifier 88 identifies (step 132) ad retrieves one or more answers for the question. Note that theanswer identifier 88 can access the Internet or the Web for answers. - The
generator 54 can also include adatabase 90 of relevant information to be accessed by different elements of thegenerator 54. Thedatabase 90, can be a relational database, an object database or other forms of database. - After the answer is generated, the
output device 56, such as a monitor, a printer or a voice synthesizer, can present the answer to the user. - FIG. 4A shows one
physical embodiment 150 implementing one embodiment of the invention, preferably in software and hardware. Theembodiment 150 includes aserver computer 152 and a number of client computers, such as 154, which can be a personal computer. Each client computer communicates to theserver computer 152 through a dedicated communication link, or acomputer network 156. In one embodiment, the link can be the Internet, intranet or other types of private-public networks. - FIG. 4B shows one embodiment of a
client computer 154. It typically includes abus 159 connecting a number of components, such as aprocessing unit 160, amain memory 162, an I/O controller 164, aperipheral controller 166, agraphics adapter 168, acircuit board 180 and anetwork interface adapter 170. The I/O controller 164 is connected to components, such as aharddisk drive 172 and afloppy disk drive 174. Theperipheral controller 166 can be connected to one or more peripheral components, such as akeyboard 176 and amouse 182. Thegraphics adapter 168 can be connected to amonitor 178. Thecircuit board 180 can be coupled to audio signals 181; and thenetwork interface adapter 170 can be connected to anetwork 120, which can be the Internet, an intranet, the Web or other forms of networks. Theprocessing unit 160 can be an application specific chip. - Different elements in the
system 50 may be in different physical components. For example, theinput device 52 and theoutput device 56 may be in a client computer; and theanswer generator 54 may reside in a server computer. In another embodiment, theinput device 52, theoutput device 56, theanswer generator 54 other than thedatabase 90 are in a client computer; and thedatabase 90 is in a server computer. In another situation, thedatabase 90 can reside in a storage medium in a client computer, or with part of it in the client computer and another part in the server computer. In a fourth embodiment, thesystem 50 is in a client computer. Yet in another embodiment, theinput device 52 and theoutput device 56 are in a client computer; theanswer generator 54 other than thedatabase 90 is in a middleware apparatus, such as a Web server; and thedatabase 90 with its management system are in a back-end server, which can be a database server. Note that different elements of theanswer generator 54 can also reside in different components. - In this invention, the question can be on a subject, which can be broad or narrow. In one embodiment, the subject can cover mathematics or history, or it can cover the JAVA programming language. In another embodiment, the subject covers information in a car, such as a Toyota Camry, and the user wants to understand this merchandise before buying it. In yet another embodiment, the subject covers the real estate market in a certain geographical area, and again the user wants to understand the market before buying a house.
- In one embodiment, a question can be defined as an inquiry demanding an answer; and an answer can be defined as a statement satisfying the inquiry.
- The question can be a natural-language question, which is a question used in our everyday language. A natural-language question can be in English or other languages, such as French. Examples of natural-language questions are:
- Who is the President?
- Like cream of mushroom soup? A statement that is not based on a natural language can be a statement that is not commonly used in our everyday language. Examples are:
- For Key in Key-Of(Table) do
- Do while x>2
- In one embodiment, one grammatical rule is that a question is made of phrases; another grammatical rule is that every phrase is made of one or more words. Such rules can define a grammatical structure. A question formed under such rules is grammatically context-free, and the question is in a context-free grammatical structure.
- FIG. 5 shows examples of ways to regularize the question. The
question regularizer 80 regularizes words in the question, for example, by replacing certain words in the question with their roots. One objective of the regularizer is to reduce the size of thedatabase 90 and the amount of computation required to analyze the question. - In one embodiment, the
regularizer 80 identifies every word in the question. Then it replaces words with their roots if they are not already in their root forms. For example, the regularizer changes verbs (step 202) of different forms in the question into their present tense, and nouns (step 204) into singular. - One approach to implement the replacement process is based on a hashing function. Every word in the question can be hashed into a hash value. In one embodiment, each character is represented by eight bits, such as by its corresponding eight-bit ASCII codes. The hashing function is performed by first pairing characters together in every word of the question. If a word has an odd number of characters, then the last character of the word is paired with zero. Each paired characters becomes a sixteen-bit number. Every word could have a number of sixteen-bit numbers. The character does not have to be represented by the eight-bit ASCII codes. In another embodiment, with each character represented by its sixteen-bit unicode, the characters are not aired. Again every word could have a number of sixteen-bit numbers.
- For a word, add all of its sixteen-bit numbers, and represent the sum by a thirty-two bit number. For the thirty-two bit number, add the first two bytes and throw away the carry to generate a twenty-four bit number. This number is the hash value of the word. In one embodiment, each hash value can be used to represent two different words. One word can be in one language and the other in another language, with both languages represented by unicodes. A 16 Mbit memory could be used to hold different combinations of twenty-four bit hash values to represent different words. This approach should be applicable to most natural languages.
- In one embodiment, commonly-used words have been previously hashed and stored in the
database 90. There are also tables generated that link the hash values of those words with the hash values of their root forms. Then, the hash values of words in the question are compared to hash values in the tables and may be replaced by root-forms hash values. For example, the hash values of verbs of different forms in the question are mapped to and replaced by the hash values of their present tenses, and similarly, the hash values of plural nouns are mapped to and replaced by their corresponding singular form hash values. - In one embodiment, after some of the words in the question have been regularized, the
phrase identifier 82 can identify phrases in the question. FIG. 6 shows oneset 124 of steps related to identifying phrases. Note that the process of identifying does not have to include the process of understanding, determining its presence in the database, or extracting. - In one embodiment, the identifier identifies phrases from the beginning or the first word (step252) of the question. It identifies the first word in the question, and then determines if the first word is in the
database 90. If it is, it will be classified as a phrase of the question. Then, the identifier identifies the first two words. If there is a corresponding term with such two words in thedatabase 90, then the two words are classified as another phrase of the question. - The phrase determination process can again be done through a hashing function. One approach is to add the hash values of each of the words in a phrase. If the sum has more than 24 bits, throw away the carry. The remaining 24 bits would be the hash value of the phrase. For example, the two words in the question can be hashed into a hash value, which is compared to hash values in the
database 90. If such a hash value exists in thedatabase 90, then the two words are classified as a phrase. In one embodiment, this process continues on up to the first twenty words in the question. - In one embodiment, when a hash value for a certain number of words does not exist, the identifier stops adding another word to identify phrases in the question. However, a hash value that exists in the
database 90 does not mean that its corresponding word or words can have independent meaning. The existence of a hash value in thedatabase 90 can imply that thephrase identifier 82 should continue on adding words to look for phrases. For example, theidentifier 82 should continue on adding words to identify the longest matching phrase, which can be a phrase with six words. For example, the term, “with respect”, may not be a phrase, or does not have independent meaning. But the hash value of such a term can be in thedatabase 90. Then the identifier adds the next word in the question to determine if the three-word combination exists in thedatabase 90. If the third word is the word “to”, then the three-word combination is a preposition with independent meaning, and can have a hash value in thedatabase 90. - After identifying all of the phrases from the first word, the identifier starts from identifying (step254) phrases from the second word of the question, and performs similar identification process as it has done from the first word. One difference is that the starting point of the analysis is the second word.
- As an example, the question is, “Are ball bearings round?” The identifier starts from the word, “are”, and stops after the word, “balls”, because there is no hash value for the term, “are ball”. Then, the identifier starts from the word, “ball”, and finds a hash value. This suggests that the identifier should continue on, and found the hash value for the term, “ball bearings”.
- The identifier can continue on identifying phrases from the remaining words (step256) in the question. The starting point of the analysis moves from one word to the next, down the question, until all of the words in the sentence have been exhausted.
- At the end of phrase identification, the identifier should have identified all of the phrases in the question with corresponding phrases in the
database 90. In one embodiment, the identifier then removes (step 258) words in the question that are not in any identified phrases. For example, there is a word, “xyz”, in the sentence, which is not found in any of the identified phrases. That word will not be considered in subsequent analysis, or will be ignored. In essence, that word is removed from the question. - From the identified phrases, the
phrase identifier 82 generates (step 260) a number of phrased questions. Each phrased question is a combination of one or more identified phrases that match the question. All of the phrased questions cover different combinations of the identified phrases that match the question. - For example, the question is “Cash cow?”
- There can be two phrased questions, and they are:
- 1. “Cash cow”?
- 2. “Cash cow”?
- The first phrased question has two phrases, each with one word. The second phrased question has only one phrase, with two words.
- Many languages, such as English, favor the use of multiple words that give a different meaning if combined together. Depending on how words are phrased together, the phrased questions can have very different meanings. As in the above example, the meaning of “cash cow” is different from the meaning of, “cash” and “cow”, individually.
- Based on the one or more phrased questions, the
question structure identifier 84 identifies one or more question structures. FIG. 7 shows oneset 126 of steps related to identifying question structures. - In one embodiment, phrases in the
database 90 are categorized (step 302). A phrase can belong to one or more categories. A category can be a group of phrases, with one or more common characteristics, which can be related to a subject matter. For example, there are two categories and they are Congress and finance. Then, one semantic rule can be that the phrase “bill” belongs to both categories, while another semantic rule can be that the phrase “Capital Asset Pricing Model” belongs to the category of finance. - For each phrased question, each of its phrases can be linked (step302) by a linker to one or more categories. For example, for the phrased question, “cash” “cow”, the phrase “cash” can be linked to the categories of finance, banking and payment; and the phrase “cow” can be linked to the categories of animals and diary products. For the phrased question, “cash cow”, the phrase “cash cow” can be linked to the categories of finance and banking.
- Each category can be given a score. In one embodiment, the score denotes the importance of the category, or the relevancy of the category to the question. The score can depend on the meaning of the category. For example, the category of Congress is given 10 points, and the category of finance is given 30 terms because more people ask about finance than Congress. The scores can depend on the subject the user is asking. For example, if the question is about travel, the category on city can be given 20 points, and the category on animal 5 points. Scoring categories can be done dynamically. For example, after the question has been determined to be in the area of finance, the category on insect can be dynamically given 0.1 point or even 0 points, while the category on investment can be given 100 points. In this example, one semantic rule can be that in the finance area, the score of the category of investment is higher than that of the category of insect.
- In another example, the scores given to interrogative pronouns can depend on the type of questions asked. In the travel domain or in questions on traveling, the categories for “how”, “where”, “what” and “when” can be given higher scores than the category for “who”.
- Each phrase in a phrased question can belong to more than one categories. With the categories having scores, each phrase belonging to multiple categories can have more than one scores. In one embodiment, the category with the highest score is selected to be the category of that phrase, or to be the score of that categorized phrase (step304).
- In one embodiment, the score of at least one phrase depends on information about the user. This information can be specific to that user. FIG. 8 shows examples of factors affecting the scores. In one embodiment, the information about the user is more than the fact that the user just asked the system50 a question.
- The information can be related to the question's
subject matter 350, identified by the user. For example, thesystem 50 can ask the user the subject of his question. In another approach, before the user asks a question, the user has to select one subject of interest. All of his question would be considered to be related to that subject. - The information can be related to the user's
previous question 352. For example, the user has been asking questions related to health, and his question has the word, virus, in it. Thesystem 50 would not consider the question to be related to computer virus, but would focus on the type of virus affecting our health. - In one embodiment on previous questions, the input and output devices are in a client computer used by the user to ask questions, and the answer generator is in a server computer. At the request of the server computer, the Web browser in the client computer stores the question asked by the user in cookies. The next time when the user accesses the server computer to ask another question, the cookies are sent back to the server computer. The responses generated by the server computer depend on information in the cookies, such as the one or more questions previously asked by the user.
- In another embodiment, previous questions can be stored in, for example, HTML forms, which support hidden variables, or HTML scripts written in JavaScript, which supports variables. For the HTML forms example, the question format identifier can generate a set of instructions to represent question formats to be sent to the user. The instructions can be written in HTML form. During a question/answer interactive session between the user and the system, the input device remembers the one or more question asked by the user and the question formats selected by the user. After a user has selected a question format or asked a new question, the input device can send it to the answer generator. The format sent can also include one or more previous questions asked by the user during the same session. Those questions are stored in the hidden variables of the question format. In this example, during the interactive session, all of the user's inputs can be stored. Whenever anything is sent to the answer generator, all of the user's previous inputs can be sent to the generator in the hidden variables.
- The information can be related to a profile of the user354. For example, the user is asked to fill in a questionnaire about himself before he starts asking question. His profile can include his language skill, 356, such as the languages he prefers his answer to be in; his areas of interest, 358, such as the types of songs he likes; and his ethnic background, 360. For example, the user is an Egyptian. Then, categories related to Egypt can be given higher scores. Such information would help the
system 50 tailor more accurate and relevant responses to him. In one embodiment, a user enters his identifier when he starts to use the system. Then, next time when he uses thesystem 50, based on his identification, thesystem 50 can retrieve his profile. His profile can be updated based on his usage of thesystem 50, for example, based on questions he just asked. Again, his identification can be stored in cookies. - In yet another embodiment,
certain information 357 in the user's profile does not have to be directly entered by the user. As an example, the invention can be implemented in a client-server environment, with the client having an IP address. At least a portion of the answer generator resides in a server, and at least a portion of the input device in a client. Certain information in the user's profile may depend on theIP address 359. After the client has established, for example, a HTTP session with the server, the client's IP address would be passed to the server. Based on the source IP address, the server can go to a domain name database, such as those hosted by Network Solution Incorporated, to access the domain name of the client. The domain name gives a number of information, such as the point of presence of the Internet service provider used by the client. The server would then be aware, for example, the approximate ZIP code of the client, or the approximate geographical location of the client. As an example, such information can be used in the following way. If the user is approximately located in San Francisco, and he is asking for hotel information in Boston, the server can assume that the user intends to travel to Boston. Based on such an assumption, the server can send to the client answers related to car rental information and flight ticket information when responding to his question for hotel information. - Based on the user's question, the
system 50 can ask the user to refine the question. For example, the question includes the word “current”. Thesystem 50 can ask the user if his question is related to the subject of electricity or time or other physical phenomena. Based on the system'sinquiry 362, information related to the user's question can be acquired to improve on the responses to the question. In this embodiment, there can be multiple interactive sessions between the user and thesystem 50. The system can ask the user more than one question so as to refine the answer. For example, after the user has responded that the word “current” is related to other physical phenomena, thesystem 50 can ask the user if the question is related to wind or ocean or other physical phenomena so as to better understand the question. - In one embodiment, the score of at least one phrase depends on the subject matter of the question. Information on the subject matter of the question, or the domain knowledge, does not have to be from the user. For example, the
system 50 can be tailored for a specific subject, such as information related to a specific company, including that company's products. That system can be designed to answer questions related to the company, with many phrases, question formats and answer formats focused on the company. For example, the company is a hardware company, and the user asks the question, “Do you have nails?” Thesystem 50 would not interpret the question to refer to nails as in finger nails. Thesystem 50 assumes the question to be related to nails, as in screws and nails, and responds accordingly. In another embodiment, the system is tailored to more than one subject matter, and can be switched from one subject matter to another using the same database. The switch can be done, for example, by adjusting the scores of different categories based on their relevancy to the subject matter. - In one embodiment, based on information related to the user and/or the subject matter of the question, scores on categories and, in turn, phrases can be changed. The change can be dynamic. In other words, scores are modified as the system gains more information. This can be done, for example, by applying multipliers to scores of categories to be changed. In another embodiment, after phrases have been categorized and before the scores of the categorized phrases are determined, those scores are changed according to the information related to the user and/or the subject matter of the question. In yet another embodiment, due to changes in the scores of the categories, a phrase previously linked to a category is modified to be linked to another category.
- In one embodiment, after categorizing and scoring each phrase in a phrased question, the structure identifier generates (step306) a number of question structures. Each phrase in the question can be linked to a category, and each phrased question can be represented by the corresponding categories. In one embodiment, the categorized representation of each phrase question can be known as a question structure, or a question structure can be a list of categories. For example, the question structure of the phrase question, “cash” “cow” can be “finance” “animals”, and the question structure of the phrase question “cash cow” can be “finance”. In this example, the question, “Cash cow?” is linked to two question structures.
- In another embodiment, the number of question structures generated can be reduced, which could increase the speed to generate a response, and could also reduce ambiguity in the question. The method is by reducing the number of categories. One way is to form categories of categories, or a hierarchy of categories. Each category can be given a name. With each question structure being a list of categories, each question structure can be represented by a list of category names. In one embodiment, the
phrase identifier 82 can operate on the list of category names to determine category-of-categories. - The category-of-category approach can be explained by the following example. The original question includes the phrase, “San Jose of California”. “San Jose” is under the category of city, “of” is under the category of “preposition”, and “California” is under the category of State. One semantic rule may be that there is a “City of State” category to replace the list of categories “city” “preposition” “State”.
- This type of category-of-categories analysis can be extended into a category hierarchy. The “city”, “preposition” and “State” can be considered as first level categories, while the “city of State” category can be considered as a second level category. The method to identify higher level categories can be the same as the method to identify second level categories based on first level categories, as long as each category is given a name. For example, a third level category can replace a list of second level categories.
- At the end of the category-of-categories analysis, different level categories can be to classified simply as categories. This approach can reduce the number of categories. With fewer categories, some question structures might be identical. Thus, this approach may reduce the number of question structures also.
- In one embodiment, one semantic rule is that a higher level category is assigned a higher score than its lower level categories. For example, the “city of State” category has a higher score than the “city”, “preposition” and “State” categories.
- The
question structure identifier 84 can select a number of the generated question structures. In one embodiment, the structure identifier provides (step 308) a score to each question structure by summing the scores of all of its categories. Thequestion structure identifier 84 then selects (step 310), for example, the question structure with the highest score to be the question structures representing the question. In one example, the identifier selects the structures with the top five highest scores to be the structures representing the question. - In one embodiment, after the question structures representing the question have been selected, the
question format identifier 86 identifies one or more question formats in thedatabase 90. FIG. 9 shows one set of steps related to identifying question formats. - Each question format can be a pre-defined question with one or more phrases and one or more categories. The following can be a question format:
- What is “a financial term”? The question, “What is preferred stock?”, falls under the above question format.
- Each category in a question format has a number of corresponding phrases. For example, the corresponding phrases of the category “major city” can include all of the cities in the United States with population exceeding one million people.
- The question formats can be pre-defined and stored in the
database 90. One way to generate them can be based on commonly-asked questions. For example, if more than twenty people ask the same or substantially similar question when they use thesystem 50, a system administrator can generate a question format for that question structure. To illustrate, more than twenty people asked the following questions, or a variation of the following questions: - A list of restaurants in San Francisco?
- Restaurants in San Francisco?
- Where can I find some good restaurants in San Francisco? All of these questions have a set of similar key words, which are restaurant and San Francisco. The
system 50, after cataloging twenty occurrences of such questions, provides one of the twenty questions to the system administrator, who can then generate the following question format: - Would you recommend some good restaurants in “major city” ?
- There are a number of ways to identify question formats. A question structure can have one or more categories. In one embodiment, for a question structure, the question format identifier identifies every question format that has all of the categories in that question structure (step402). There can be situations when a question structure has a number of categories, and no question format in the
database 90 has all of the categories. In one embodiment, for a question structure, the question format identifier identifies question formats that have at least one category in the question structure. - Based on the question structures, there can be a number of question formats identified. Then, the
question format identifier 86 can select (step 404) one or more of them. One selection criterion is based on scores of the question formats. Each question format includes one or more categories, and each category has a score. The sum of all of the scores of the categories in a question format gives the question format a score. In one embodiment, the question format with the highest score is selected. In another embodiment, the five question formats with the highest scores are selected. - A category in a question format can have a default value. Each category typically has many phrases. In one embodiment, one of the phrases is selected to be the default phrase (step406) of the category in the question format. That phrase can be the corresponding phrase in the original question leading to the selection of the category and the question format. For example, the question is, “What is the temperature in San Francisco?” The question format selected is, “What is the temperature in ‘city’?” Instead of the generic term “city” , the question format becomes, “What is the temperature in ‘San Francisco’?” In other words, San Francisco has been chosen to be the default city.
- In one embodiment, the
system 50 allows (step 130) the user to pick one or more of the selected question formats. This can be done by the question format identifier generating a number of instructions representing the selected question formats, and sending the instructions to theoutput device 56. In one example, the browser in theoutput device 56, based on the instructions, displays the selected question formats to allow the user to pick. - The
output device 56 can show the user all of the selected question formats. Next to each of the selected question formats there can be an enter icon. If the user clicks the enter icon, that question format would be picked as the selected one. - The user can also choose any one of the phrases within each category of a question format. For example, the question format picked is, “What is the temperature in ‘San Francisco’?” And the user decides to find out the temperature in Los Angeles. In one embodiment, the user can click the phrase “San Francisco”, then a list of cities shows up on the
output device 56. The user can scroll down the list to pick Los Angeles. Then, by clicking the enter icon next to the question, the user would have selected the question format, “What is the temperature in ‘Los Angeles’?” - After one or more question formats have been picked by the user, the
answer identifier 88 identifies one or more answers for the user. FIG. 10 shows oneset 132 of steps related to identifying answer. - In one embodiment, each question format has its corresponding answer format. The
answer identifier 88 retrieves (step 452) one or more answer formats for each question format. The answer format can be an answer or can be an address of an answer. In situations where the answer format is an address of an answer, the answer identifier can also access (step 454) the answer based on the answer format. - As an example, the answer format of a question format is the URL of a Web page. If the user picks that question format, the
answer identifier 88 would retrieve the corresponding answer format, and fetch the one or more Web pages with the retrieved URL. - In another embodiment, based on each of the answer formats, a set of instructions are generated to search for information, for example, from different databases or other sources, such as the Web. The instructions can be queries written, for example, in SQL, or HTTP.
- In another embodiment, as the output device shows a list of selected question formats for the user to pick, the
output device 56 also shows the answer to the question format with the highest score. - There are different ways to implement the present invention. In one embodiment, the
phrase identifier 82 can identify a few phrases, and then thequestion structure identifier 84 can generate a few question structures. As long as there are, for example, ten question structures with scores more than a threshold value, thesystem 50 would stop looking for additional question structures. If there are only nine such structures, thephrase identifier 82 would identify some more phrases, and thestructure identifier 84 would generate more question structures. In other words, thesystem 50 does not have to look for all phrases in the question before question structures are identified. The threshold value can be set by experience. For example, from past usage, maximum scores of question structures in certain subject areas, such as the traveling domain, are typically less than eighty. Then, for those types of questions, thequestion structure identifier 84 could set the threshold value to be seventy five. This approach would speed up the time required to respond to the question. - Another way to speed up the response time is through focusing on a set of question formats in the database. The question formats can be grouped together based on common characteristics. For example, all formats related to San Francisco are grouped together. Then based on information about the subject matter and/or the user, such as the user is asking questions about San Francisco, those formats would be selected to have one or more of them identified by the
question format identifier 86. In another embodiment, if the question is related to San Francisco, the scores of formats related to San Francisco would be multiplied by a factor of, for example, five. This could increase the chance of finding more relevant question formats for the user, and, in turn, more relevant answer to the question. - Note that the answer does not have to be presented by the
output device 56 in the same language as the question. The database can include information of different languages. For example, the user can ask the question in English. The subsequent analysis can be in English, with, for example, the question formats also in English. Then, each selected question format is transformed into instructions, with phrases or categories in the format translated into their equivalent terms in other languages. At least one of those categories can be selected in view of a phrase in the question. The translation can be done, for example, through unicodes. As an illustration, the English name of a person is translated into that person's name as known in his native language. After the transformation, the instructions can be used to search for or retrieve one or more answers to the question. - A different embodiment is that the system administrator can previously define certain answer formats to be in French, or to be the URL of a French Web site for the answer. French information would be retrieved to be the answers.
- In yet another embodiment to have answers in a language different from the question, the
regularizer 80 serves the function of a translator by translating the question into the other language. From that point onwards, the analysis will be in the other language. For example, the question is translated into German. Subsequently, phrases, structures, formats and answers would all be in German. - One embodiment includes a computer readable media containing computer program code. The code when executed by a computer causes the computer to perform at least some of the steps of the present invention, such as some of those defined in FIG. 3. In another embodiment, a signal is sent to a computer causing the computer to perform at least some of the steps of the present invention, such as some of those defined in FIG. 3. This signal can include the question, or a representation of the question, asked by the user. The computer can include or can gain access to the
database 90. - Note that different embodiments of the present invention can be implemented in software or in hardware. For example, steps shown in FIG. 3 or the answer generator shown in FIG. 2, can be implemented in hardware or in software or in firmware. The implementation process should be obvious to those skilled in the art.
- Other embodiments of the invention will be apparent to those skilled in the art from a consideration of this specification or practice of the invention disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.
Claims (33)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/060,120 US20020128818A1 (en) | 1996-12-02 | 2002-01-28 | Method and system to answer a natural-language question |
US10/727,701 US6865370B2 (en) | 1996-12-02 | 2003-12-03 | Learning method and system based on questioning |
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/758,896 US5836771A (en) | 1996-12-02 | 1996-12-02 | Learning method and system based on questioning |
US09/139,174 US5934910A (en) | 1996-12-02 | 1998-08-24 | Learning method and system based on questioning |
US09/347,184 US6501937B1 (en) | 1996-12-02 | 1999-07-02 | Learning method and system based on questioning |
US09/387,932 US6498921B1 (en) | 1999-09-01 | 1999-09-01 | Method and system to answer a natural-language question |
US10/060,120 US20020128818A1 (en) | 1996-12-02 | 2002-01-28 | Method and system to answer a natural-language question |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/387,932 Continuation US6498921B1 (en) | 1996-12-02 | 1999-09-01 | Method and system to answer a natural-language question |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/758,896 Continuation US5836771A (en) | 1996-12-02 | 1996-12-02 | Learning method and system based on questioning |
US10/727,701 Continuation US6865370B2 (en) | 1996-12-02 | 2003-12-03 | Learning method and system based on questioning |
Publications (1)
Publication Number | Publication Date |
---|---|
US20020128818A1 true US20020128818A1 (en) | 2002-09-12 |
Family
ID=23531912
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/387,932 Expired - Lifetime US6498921B1 (en) | 1996-12-02 | 1999-09-01 | Method and system to answer a natural-language question |
US10/060,120 Abandoned US20020128818A1 (en) | 1996-12-02 | 2002-01-28 | Method and system to answer a natural-language question |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/387,932 Expired - Lifetime US6498921B1 (en) | 1996-12-02 | 1999-09-01 | Method and system to answer a natural-language question |
Country Status (1)
Country | Link |
---|---|
US (2) | US6498921B1 (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050071216A1 (en) * | 2003-09-30 | 2005-03-31 | Microsoft Corporation | Interactive network guide |
US20050143999A1 (en) * | 2003-12-25 | 2005-06-30 | Yumi Ichimura | Question-answering method, system, and program for answering question input by speech |
US20060004724A1 (en) * | 2004-06-03 | 2006-01-05 | Oki Electric Industry Co., Ltd. | Information-processing system, information-processing method and information-processing program |
US20060167678A1 (en) * | 2003-03-14 | 2006-07-27 | Ford W R | Surface structure generation |
US20070067155A1 (en) * | 2005-09-20 | 2007-03-22 | Sonum Technologies, Inc. | Surface structure generation |
US20070198499A1 (en) * | 2006-02-17 | 2007-08-23 | Tom Ritchford | Annotation framework |
US20090162824A1 (en) * | 2007-12-21 | 2009-06-25 | Heck Larry P | Automated learning from a question and answering network of humans |
US7925676B2 (en) | 2006-01-27 | 2011-04-12 | Google Inc. | Data object visualization using maps |
US7953720B1 (en) | 2005-03-31 | 2011-05-31 | Google Inc. | Selecting the best answer to a fact query from among a set of potential answers |
US8065290B2 (en) | 2005-03-31 | 2011-11-22 | Google Inc. | User interface for facts query engine with snippets from information sources that include query terms and answer terms |
US8239751B1 (en) * | 2007-05-16 | 2012-08-07 | Google Inc. | Data from web documents in a spreadsheet |
US8239394B1 (en) | 2005-03-31 | 2012-08-07 | Google Inc. | Bloom filters for query simulation |
US20130196305A1 (en) * | 2012-01-30 | 2013-08-01 | International Business Machines Corporation | Method and apparatus for generating questions |
US20130246065A1 (en) * | 2006-04-03 | 2013-09-19 | Google Inc. | Automatic Language Model Update |
US8954426B2 (en) | 2006-02-17 | 2015-02-10 | Google Inc. | Query language |
US8954412B1 (en) | 2006-09-28 | 2015-02-10 | Google Inc. | Corroborating facts in electronic documents |
US9087059B2 (en) | 2009-08-07 | 2015-07-21 | Google Inc. | User interface for presenting search results for multiple regions of a visual query |
US9135277B2 (en) | 2009-08-07 | 2015-09-15 | Google Inc. | Architecture for responding to a visual query |
US9484034B2 (en) | 2014-02-13 | 2016-11-01 | Kabushiki Kaisha Toshiba | Voice conversation support apparatus, voice conversation support method, and computer readable medium |
US20160350279A1 (en) * | 2015-05-27 | 2016-12-01 | International Business Machines Corporation | Utilizing a dialectical model in a question answering system |
US9530229B2 (en) | 2006-01-27 | 2016-12-27 | Google Inc. | Data object visualization using graphs |
US9892132B2 (en) | 2007-03-14 | 2018-02-13 | Google Llc | Determining geographic locations for place names in a fact repository |
US10102275B2 (en) | 2015-05-27 | 2018-10-16 | International Business Machines Corporation | User interface for a query answering system |
US11030227B2 (en) | 2015-12-11 | 2021-06-08 | International Business Machines Corporation | Discrepancy handler for document ingestion into a corpus for a cognitive computing system |
US11074286B2 (en) | 2016-01-12 | 2021-07-27 | International Business Machines Corporation | Automated curation of documents in a corpus for a cognitive computing system |
US11308143B2 (en) | 2016-01-12 | 2022-04-19 | International Business Machines Corporation | Discrepancy curator for documents in a corpus of a cognitive computing system |
US11392778B2 (en) * | 2014-12-29 | 2022-07-19 | Paypal, Inc. | Use of statistical flow data for machine translations between different languages |
Families Citing this family (99)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6498921B1 (en) * | 1999-09-01 | 2002-12-24 | Chi Fai Ho | Method and system to answer a natural-language question |
US6763342B1 (en) * | 1998-07-21 | 2004-07-13 | Sentar, Inc. | System and method for facilitating interaction with information stored at a web site |
US7877774B1 (en) * | 1999-04-19 | 2011-01-25 | At&T Intellectual Property Ii, L.P. | Browsing and retrieval of full broadcast-quality video |
US9171545B2 (en) * | 1999-04-19 | 2015-10-27 | At&T Intellectual Property Ii, L.P. | Browsing and retrieval of full broadcast-quality video |
US9076448B2 (en) * | 1999-11-12 | 2015-07-07 | Nuance Communications, Inc. | Distributed real time speech recognition system |
US7725307B2 (en) * | 1999-11-12 | 2010-05-25 | Phoenix Solutions, Inc. | Query engine for processing voice based queries including semantic decoding |
US6898411B2 (en) * | 2000-02-10 | 2005-05-24 | Educational Testing Service | Method and system for online teaching using web pages |
JP3587120B2 (en) * | 2000-03-15 | 2004-11-10 | 日本電気株式会社 | Questionnaire response analysis system |
US8510668B1 (en) | 2000-04-03 | 2013-08-13 | Google Inc. | Indicating potential focus in a user interface |
US7356604B1 (en) * | 2000-04-18 | 2008-04-08 | Claritech Corporation | Method and apparatus for comparing scores in a vector space retrieval process |
US7120627B1 (en) * | 2000-04-26 | 2006-10-10 | Global Information Research And Technologies, Llc | Method for detecting and fulfilling an information need corresponding to simple queries |
US6999963B1 (en) | 2000-05-03 | 2006-02-14 | Microsoft Corporation | Methods, apparatus, and data structures for annotating a database design schema and/or indexing annotations |
US6993475B1 (en) * | 2000-05-03 | 2006-01-31 | Microsoft Corporation | Methods, apparatus, and data structures for facilitating a natural language interface to stored information |
US7010606B1 (en) | 2000-06-05 | 2006-03-07 | International Business Machines Corporation | System and method for caching a network connection |
US6963876B2 (en) * | 2000-06-05 | 2005-11-08 | International Business Machines Corporation | System and method for searching extended regular expressions |
US6931393B1 (en) | 2000-06-05 | 2005-08-16 | International Business Machines Corporation | System and method for enabling statistical matching |
US6745189B2 (en) * | 2000-06-05 | 2004-06-01 | International Business Machines Corporation | System and method for enabling multi-indexing of objects |
US6823328B2 (en) * | 2000-06-05 | 2004-11-23 | International Business Machines Corporation | System and method for enabling unified access to multiple types of data |
US7016917B2 (en) * | 2000-06-05 | 2006-03-21 | International Business Machines Corporation | System and method for storing conceptual information |
US6611837B2 (en) * | 2000-06-05 | 2003-08-26 | International Business Machines Corporation | System and method for managing hierarchical objects |
US6675010B1 (en) * | 2000-06-22 | 2004-01-06 | Hao Ming Yeh | Mobile communication system for learning foreign vocabulary |
US7142662B2 (en) | 2000-07-11 | 2006-11-28 | Austin Logistics Incorporated | Method and system for distributing outbound telephone calls |
US7103173B2 (en) | 2001-07-09 | 2006-09-05 | Austin Logistics Incorporated | System and method for preemptive goals based routing of contact records |
JP4686905B2 (en) * | 2000-07-21 | 2011-05-25 | パナソニック株式会社 | Dialog control method and apparatus |
US6413100B1 (en) * | 2000-08-08 | 2002-07-02 | Netucation, Llc | System and methods for searching for and delivering solutions to specific problems and problem types |
JP2002278977A (en) * | 2001-03-22 | 2002-09-27 | Fujitsu Ltd | Device and method for answering question and question answer program |
US20030004702A1 (en) * | 2001-06-29 | 2003-01-02 | Dan Higinbotham | Partial sentence translation memory program |
WO2003005166A2 (en) | 2001-07-03 | 2003-01-16 | University Of Southern California | A syntax-based statistical translation model |
US7715546B2 (en) | 2001-07-09 | 2010-05-11 | Austin Logistics Incorporated | System and method for updating contact records |
US7054434B2 (en) | 2001-07-09 | 2006-05-30 | Austin Logistics Incorporated | System and method for common account based routing of contact records |
AU2003210393A1 (en) * | 2002-02-27 | 2003-09-09 | Michael Rik Frans Brands | A data integration and knowledge management solution |
US20030182391A1 (en) * | 2002-03-19 | 2003-09-25 | Mike Leber | Internet based personal information manager |
WO2004001623A2 (en) | 2002-03-26 | 2003-12-31 | University Of Southern California | Constructing a translation lexicon from comparable, non-parallel corpora |
JP3698689B2 (en) * | 2002-03-27 | 2005-09-21 | 富士通株式会社 | Teaching material defect location notification method and teaching material failure location notification device |
CA2487739A1 (en) * | 2002-05-28 | 2003-12-04 | Vladimir Vladimirovich Nasypny | Method for synthesising a self-learning system for knowledge acquisition for text-retrieval systems |
AU2003265903A1 (en) * | 2002-09-03 | 2004-03-29 | Himanshu Bhatnagar | Interview automation system for providing technical support |
JP2004118740A (en) * | 2002-09-27 | 2004-04-15 | Toshiba Corp | Question answering system, question answering method and question answering program |
US20040166484A1 (en) * | 2002-12-20 | 2004-08-26 | Mark Alan Budke | System and method for simulating training scenarios |
US20040254794A1 (en) * | 2003-05-08 | 2004-12-16 | Carl Padula | Interactive eyes-free and hands-free device |
US20050239022A1 (en) * | 2003-05-13 | 2005-10-27 | Harless William G | Method and system for master teacher knowledge transfer in a computer environment |
US7797146B2 (en) | 2003-05-13 | 2010-09-14 | Interactive Drama, Inc. | Method and system for simulated interactive conversation |
US20050239035A1 (en) * | 2003-05-13 | 2005-10-27 | Harless William G | Method and system for master teacher testing in a computer environment |
US8548794B2 (en) | 2003-07-02 | 2013-10-01 | University Of Southern California | Statistical noun phrase translation |
US8296127B2 (en) | 2004-03-23 | 2012-10-23 | University Of Southern California | Discovery of parallel text portions in comparable collections of corpora and training using comparable texts |
US8666725B2 (en) | 2004-04-16 | 2014-03-04 | University Of Southern California | Selection and use of nonstatistical translation components in a statistical machine translation framework |
US8600728B2 (en) | 2004-10-12 | 2013-12-03 | University Of Southern California | Training for a text-to-text application which uses string to tree conversion for training and decoding |
KR100723404B1 (en) * | 2005-03-29 | 2007-05-30 | 삼성전자주식회사 | Apparatus and method for processing speech |
US8676563B2 (en) | 2009-10-01 | 2014-03-18 | Language Weaver, Inc. | Providing human-generated and machine-generated trusted translations |
US8886517B2 (en) | 2005-06-17 | 2014-11-11 | Language Weaver, Inc. | Trust scoring for language translation systems |
US8666928B2 (en) * | 2005-08-01 | 2014-03-04 | Evi Technologies Limited | Knowledge repository |
US8548799B2 (en) * | 2005-08-10 | 2013-10-01 | Microsoft Corporation | Methods and apparatus to help users of a natural language system formulate queries |
US9020326B2 (en) * | 2005-08-23 | 2015-04-28 | At&T Intellectual Property Ii, L.P. | System and method for content-based navigation of live and recorded TV and video programs |
US9042703B2 (en) | 2005-10-31 | 2015-05-26 | At&T Intellectual Property Ii, L.P. | System and method for content-based navigation of live and recorded TV and video programs |
US20070073533A1 (en) * | 2005-09-23 | 2007-03-29 | Fuji Xerox Co., Ltd. | Systems and methods for structural indexing of natural language text |
US8429148B1 (en) | 2005-11-01 | 2013-04-23 | At&T Intellectual Property Ii, L.P. | Method and apparatus for automatically generating headlines based on data retrieved from a network and for answering questions related to a headline |
US10319252B2 (en) * | 2005-11-09 | 2019-06-11 | Sdl Inc. | Language capability assessment and training apparatus and techniques |
JP5169816B2 (en) * | 2006-03-01 | 2013-03-27 | 日本電気株式会社 | Question answering device, question answering method, and question answering program |
US7599861B2 (en) | 2006-03-02 | 2009-10-06 | Convergys Customer Management Group, Inc. | System and method for closed loop decisionmaking in an automated care system |
US8943080B2 (en) | 2006-04-07 | 2015-01-27 | University Of Southern California | Systems and methods for identifying parallel documents and sentence fragments in multilingual document collections |
US8379830B1 (en) | 2006-05-22 | 2013-02-19 | Convergys Customer Management Delaware Llc | System and method for automated customer service with contingent live interaction |
US7809663B1 (en) | 2006-05-22 | 2010-10-05 | Convergys Cmg Utah, Inc. | System and method for supporting the utilization of machine language |
US20070288576A1 (en) * | 2006-06-12 | 2007-12-13 | Illg Jason J | Disambiguating Responses to Questions Within Electronic Messaging Communications |
US7860815B1 (en) * | 2006-07-12 | 2010-12-28 | Venkateswara Prasad Tangirala | Computer knowledge representation format, system, methods, and applications |
US8886518B1 (en) | 2006-08-07 | 2014-11-11 | Language Weaver, Inc. | System and method for capitalizing machine translated text |
US20080040339A1 (en) * | 2006-08-07 | 2008-02-14 | Microsoft Corporation | Learning question paraphrases from log data |
US7774198B2 (en) * | 2006-10-06 | 2010-08-10 | Xerox Corporation | Navigation system for text |
US8433556B2 (en) | 2006-11-02 | 2013-04-30 | University Of Southern California | Semi-supervised training for statistical word alignment |
US9122674B1 (en) | 2006-12-15 | 2015-09-01 | Language Weaver, Inc. | Use of annotations in statistical machine translation |
WO2008078670A1 (en) * | 2006-12-22 | 2008-07-03 | Nec Corporation | Sentence rephrasing method, program, and system |
US8468149B1 (en) | 2007-01-26 | 2013-06-18 | Language Weaver, Inc. | Multi-lingual online community |
US8615389B1 (en) | 2007-03-16 | 2013-12-24 | Language Weaver, Inc. | Generation and exploitation of an approximate language model |
US8831928B2 (en) | 2007-04-04 | 2014-09-09 | Language Weaver, Inc. | Customizable machine translation service |
US8825466B1 (en) | 2007-06-08 | 2014-09-02 | Language Weaver, Inc. | Modification of annotated bilingual segment pairs in syntax-based machine translation |
US8260619B1 (en) | 2008-08-22 | 2012-09-04 | Convergys Cmg Utah, Inc. | Method and system for creating natural language understanding grammars |
US8838659B2 (en) | 2007-10-04 | 2014-09-16 | Amazon Technologies, Inc. | Enhanced knowledge repository |
US8332394B2 (en) * | 2008-05-23 | 2012-12-11 | International Business Machines Corporation | System and method for providing question and answers with deferred type evaluation |
US8275803B2 (en) | 2008-05-14 | 2012-09-25 | International Business Machines Corporation | System and method for providing answers to questions |
US9805089B2 (en) | 2009-02-10 | 2017-10-31 | Amazon Technologies, Inc. | Local business and product search system and method |
US8990064B2 (en) | 2009-07-28 | 2015-03-24 | Language Weaver, Inc. | Translating documents based on content |
US8380486B2 (en) | 2009-10-01 | 2013-02-19 | Language Weaver, Inc. | Providing machine-generated translations and corresponding trust levels |
US20110125734A1 (en) * | 2009-11-23 | 2011-05-26 | International Business Machines Corporation | Questions and answers generation |
US10417646B2 (en) | 2010-03-09 | 2019-09-17 | Sdl Inc. | Predicting the cost associated with translating textual content |
US9110882B2 (en) | 2010-05-14 | 2015-08-18 | Amazon Technologies, Inc. | Extracting structured knowledge from unstructured text |
US8892550B2 (en) | 2010-09-24 | 2014-11-18 | International Business Machines Corporation | Source expansion for information retrieval and information extraction |
US11003838B2 (en) | 2011-04-18 | 2021-05-11 | Sdl Inc. | Systems and methods for monitoring post translation editing |
US8694303B2 (en) | 2011-06-15 | 2014-04-08 | Language Weaver, Inc. | Systems and methods for tuning parameters in statistical machine translation |
US8886515B2 (en) | 2011-10-19 | 2014-11-11 | Language Weaver, Inc. | Systems and methods for enhancing machine translation post edit review processes |
US8942973B2 (en) | 2012-03-09 | 2015-01-27 | Language Weaver, Inc. | Content page URL translation |
US10261994B2 (en) | 2012-05-25 | 2019-04-16 | Sdl Inc. | Method and system for automatic management of reputation of translators |
US10621880B2 (en) | 2012-09-11 | 2020-04-14 | International Business Machines Corporation | Generating secondary questions in an introspective question answering system |
US9424341B2 (en) * | 2012-10-23 | 2016-08-23 | Ca, Inc. | Information management systems and methods |
US9152622B2 (en) | 2012-11-26 | 2015-10-06 | Language Weaver, Inc. | Personalized machine translation via online adaptation |
WO2015051397A1 (en) * | 2013-10-10 | 2015-04-16 | Quikser Pty Ltd | A server for serving answer data and a computer readable storage medium for serving answer data |
US9213694B2 (en) | 2013-10-10 | 2015-12-15 | Language Weaver, Inc. | Efficient online domain adaptation |
US9652451B2 (en) * | 2014-05-08 | 2017-05-16 | Marvin Elder | Natural language query |
US9959006B2 (en) | 2014-05-12 | 2018-05-01 | International Business Machines Corporation | Generating a form response interface in an online application |
GB201620714D0 (en) * | 2016-12-06 | 2017-01-18 | Microsoft Technology Licensing Llc | Information retrieval system |
US10740373B2 (en) | 2017-02-08 | 2020-08-11 | International Business Machines Corporation | Dialog mechanism responsive to query context |
US11182681B2 (en) | 2017-03-15 | 2021-11-23 | International Business Machines Corporation | Generating natural language answers automatically |
Citations (84)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4586160A (en) * | 1982-04-07 | 1986-04-29 | Tokyo Shibaura Denki Kabushiki Kaisha | Method and apparatus for analyzing the syntactic structure of a sentence |
US4594686A (en) * | 1979-08-30 | 1986-06-10 | Sharp Kabushiki Kaisha | Language interpreter for inflecting words from their uninflected forms |
US4597057A (en) * | 1981-12-31 | 1986-06-24 | System Development Corporation | System for compressed storage of 8-bit ASCII bytes using coded strings of 4 bit nibbles |
US4599691A (en) * | 1982-05-20 | 1986-07-08 | Kokusai Denshin Denwa Co., Ltd. | Tree transformation system in machine translation system |
US4641264A (en) * | 1981-09-04 | 1987-02-03 | Hitachi, Ltd. | Method for automatic translation between natural languages |
US4674065A (en) * | 1982-04-30 | 1987-06-16 | International Business Machines Corporation | System for detecting and correcting contextual errors in a text processing system |
US4773009A (en) * | 1986-06-06 | 1988-09-20 | Houghton Mifflin Company | Method and apparatus for text analysis |
US5070478A (en) * | 1988-11-21 | 1991-12-03 | Xerox Corporation | Modifying text data to change features in a region of text |
US5088048A (en) * | 1988-06-10 | 1992-02-11 | Xerox Corporation | Massively parallel propositional reasoning |
US5111398A (en) * | 1988-11-21 | 1992-05-05 | Xerox Corporation | Processing natural language text using autonomous punctuational structure |
US5224038A (en) * | 1989-04-05 | 1993-06-29 | Xerox Corporation | Token editor architecture |
US5278980A (en) * | 1991-08-16 | 1994-01-11 | Xerox Corporation | Iterative technique for phrase query formation and an information retrieval system employing same |
US5384703A (en) * | 1993-07-02 | 1995-01-24 | Xerox Corporation | Method and apparatus for summarizing documents according to theme |
US5386276A (en) * | 1993-07-12 | 1995-01-31 | Xerox Corporation | Detecting and correcting for low developed mass per unit area |
US5438511A (en) * | 1988-10-19 | 1995-08-01 | Xerox Corporation | Disjunctive unification |
US5500920A (en) * | 1993-09-23 | 1996-03-19 | Xerox Corporation | Semantic co-occurrence filtering for speech recognition and signal transcription applications |
US5560037A (en) * | 1987-12-28 | 1996-09-24 | Xerox Corporation | Compact hyphenation point data |
US5594641A (en) * | 1992-07-20 | 1997-01-14 | Xerox Corporation | Finite-state transduction of related word forms for text indexing and retrieval |
US5598518A (en) * | 1993-03-10 | 1997-01-28 | Fuji Xerox Co., Ltd. | Text editing apparatus for rearranging sentences |
US5625773A (en) * | 1989-04-05 | 1997-04-29 | Xerox Corporation | Method of encoding and line breaking text |
US5638543A (en) * | 1993-06-03 | 1997-06-10 | Xerox Corporation | Method and apparatus for automatic document summarization |
US5649218A (en) * | 1994-07-19 | 1997-07-15 | Fuji Xerox Co., Ltd. | Document structure retrieval apparatus utilizing partial tag-restored structure |
US5675819A (en) * | 1994-06-16 | 1997-10-07 | Xerox Corporation | Document information retrieval using global word co-occurrence patterns |
US5689716A (en) * | 1995-04-14 | 1997-11-18 | Xerox Corporation | Automatic method of generating thematic summaries |
US5696962A (en) * | 1993-06-24 | 1997-12-09 | Xerox Corporation | Method for computerized information retrieval using shallow linguistic analysis |
US5721939A (en) * | 1995-08-03 | 1998-02-24 | Xerox Corporation | Method and apparatus for tokenizing text |
US5727222A (en) * | 1995-12-14 | 1998-03-10 | Xerox Corporation | Method of parsing unification based grammars using disjunctive lazy copy links |
US5745602A (en) * | 1995-05-01 | 1998-04-28 | Xerox Corporation | Automatic method of selecting multi-word key phrases from a document |
US5752021A (en) * | 1994-05-24 | 1998-05-12 | Fuji Xerox Co., Ltd. | Document database management apparatus capable of conversion between retrieval formulae for different schemata |
US5778397A (en) * | 1995-06-28 | 1998-07-07 | Xerox Corporation | Automatic method of generating feature probabilities for automatic extracting summarization |
US5787420A (en) * | 1995-12-14 | 1998-07-28 | Xerox Corporation | Method of ordering document clusters without requiring knowledge of user interests |
US5819210A (en) * | 1996-06-21 | 1998-10-06 | Xerox Corporation | Method of lazy contexted copying during unification |
US5831853A (en) * | 1995-06-07 | 1998-11-03 | Xerox Corporation | Automatic construction of digital controllers/device drivers for electro-mechanical systems using component models |
US5848191A (en) * | 1995-12-14 | 1998-12-08 | Xerox Corporation | Automatic method of generating thematic summaries from a document image without performing character recognition |
US5850476A (en) * | 1995-12-14 | 1998-12-15 | Xerox Corporation | Automatic method of identifying drop words in a document image without performing character recognition |
US5862321A (en) * | 1994-06-27 | 1999-01-19 | Xerox Corporation | System and method for accessing and distributing electronic documents |
US5870741A (en) * | 1995-10-20 | 1999-02-09 | Fuji Xerox Co., Ltd. | Information management device |
US5883986A (en) * | 1995-06-02 | 1999-03-16 | Xerox Corporation | Method and system for automatic transcription correction |
US5892842A (en) * | 1995-12-14 | 1999-04-06 | Xerox Corporation | Automatic method of identifying sentence boundaries in a document image |
US5903860A (en) * | 1996-06-21 | 1999-05-11 | Xerox Corporation | Method of conjoining clauses during unification using opaque clauses |
US5903796A (en) * | 1998-03-05 | 1999-05-11 | Xerox Corporation | P/R process control patch uniformity analyzer |
US5905980A (en) * | 1996-10-31 | 1999-05-18 | Fuji Xerox Co., Ltd. | Document processing apparatus, word extracting apparatus, word extracting method and storage medium for storing word extracting program |
US5911140A (en) * | 1995-12-14 | 1999-06-08 | Xerox Corporation | Method of ordering document clusters given some knowledge of user interests |
US5918240A (en) * | 1995-06-28 | 1999-06-29 | Xerox Corporation | Automatic method of extracting summarization using feature probabilities |
US5937224A (en) * | 1998-03-05 | 1999-08-10 | Xerox Corporation | Cleaner stress indicator |
US5943669A (en) * | 1996-11-25 | 1999-08-24 | Fuji Xerox Co., Ltd. | Document retrieval device |
US5944530A (en) * | 1996-08-13 | 1999-08-31 | Ho; Chi Fai | Learning method and system that consider a student's concentration level |
US5946521A (en) * | 1998-03-05 | 1999-08-31 | Xerox Corporation | Xerographic xerciser including a hierarchy system for determining part replacement and failure |
US5960228A (en) * | 1998-03-05 | 1999-09-28 | Xerox Corporation | Dirt level early warning system |
US5995775A (en) * | 1998-03-05 | 1999-11-30 | Xerox Corporation | ROS pixel size growth detector |
US6006240A (en) * | 1997-03-31 | 1999-12-21 | Xerox Corporation | Cell identification in table analysis |
US6016204A (en) * | 1998-03-05 | 2000-01-18 | Xerox Corporation | Actuator performance indicator |
US6016516A (en) * | 1996-08-07 | 2000-01-18 | Fuji Xerox Co. Ltd. | Remote procedure processing device used by at least two linked computer systems |
US6023760A (en) * | 1996-06-22 | 2000-02-08 | Xerox Corporation | Modifying an input string partitioned in accordance with directionality and length constraints |
US6076086A (en) * | 1997-03-17 | 2000-06-13 | Fuji Xerox Co., Ltd. | Associate document retrieving apparatus and storage medium for storing associate document retrieving program |
US6081348A (en) * | 1998-03-05 | 2000-06-27 | Xerox Corporation | Ros beam failure detector |
US6128634A (en) * | 1998-01-06 | 2000-10-03 | Fuji Xerox Co., Ltd. | Method and apparatus for facilitating skimming of text |
US6167369A (en) * | 1998-12-23 | 2000-12-26 | Xerox Company | Automatic language identification using both N-gram and word information |
US6198885B1 (en) * | 1998-03-05 | 2001-03-06 | Xerox Corporation | Non-uniform development indicator |
US6202064B1 (en) * | 1997-06-20 | 2001-03-13 | Xerox Corporation | Linguistic search system |
US6269189B1 (en) * | 1998-12-29 | 2001-07-31 | Xerox Corporation | Finding selected character strings in text and providing information relating to the selected character strings |
US6282509B1 (en) * | 1997-11-18 | 2001-08-28 | Fuji Xerox Co., Ltd. | Thesaurus retrieval and synthesis system |
US6289304B1 (en) * | 1998-03-23 | 2001-09-11 | Xerox Corporation | Text summarization using part-of-speech |
US6308149B1 (en) * | 1998-12-16 | 2001-10-23 | Xerox Corporation | Grouping words with equivalent substrings by automatic clustering based on suffix relationships |
US6321191B1 (en) * | 1999-01-19 | 2001-11-20 | Fuji Xerox Co., Ltd. | Related sentence retrieval system having a plurality of cross-lingual retrieving units that pairs similar sentences based on extracted independent words |
US6321189B1 (en) * | 1998-07-02 | 2001-11-20 | Fuji Xerox Co., Ltd. | Cross-lingual retrieval system and method that utilizes stored pair data in a vector space model to process queries |
US6321372B1 (en) * | 1998-12-23 | 2001-11-20 | Xerox Corporation | Executable for requesting a linguistic service |
US6339783B1 (en) * | 1996-12-10 | 2002-01-15 | Fuji Xerox Co., Ltd. | Procedure execution device and procedure execution method |
US6366697B1 (en) * | 1993-10-06 | 2002-04-02 | Xerox Corporation | Rotationally desensitized unistroke handwriting recognition |
US6389435B1 (en) * | 1999-02-05 | 2002-05-14 | Fuji Xerox, Co, Ltd. | Method and system for copying a freeform digital ink mark on an object to a related object |
US6393389B1 (en) * | 1999-09-23 | 2002-05-21 | Xerox Corporation | Using ranked translation choices to obtain sequences indicating meaning of multi-token expressions |
US6411962B1 (en) * | 1999-11-29 | 2002-06-25 | Xerox Corporation | Systems and methods for organizing text |
US6430557B1 (en) * | 1998-12-16 | 2002-08-06 | Xerox Corporation | Identifying a group of words using modified query words obtained from successive suffix relationships |
US6446035B1 (en) * | 1999-05-05 | 2002-09-03 | Xerox Corporation | Finding groups of people based on linguistically analyzable content of resources accessed |
US6466213B2 (en) * | 1998-02-13 | 2002-10-15 | Xerox Corporation | Method and apparatus for creating personal autonomous avatars |
US6470334B1 (en) * | 1999-01-07 | 2002-10-22 | Fuji Xerox Co., Ltd. | Document retrieval apparatus |
US6473729B1 (en) * | 1999-12-20 | 2002-10-29 | Xerox Corporation | Word phrase translation using a phrase index |
US6493663B1 (en) * | 1998-12-17 | 2002-12-10 | Fuji Xerox Co., Ltd. | Document summarizing apparatus, document summarizing method and recording medium carrying a document summarizing program |
US6498921B1 (en) * | 1999-09-01 | 2002-12-24 | Chi Fai Ho | Method and system to answer a natural-language question |
US6501937B1 (en) * | 1996-12-02 | 2002-12-31 | Chi Fai Ho | Learning method and system based on questioning |
US6505150B2 (en) * | 1997-07-02 | 2003-01-07 | Xerox Corporation | Article and method of automatically filtering information retrieval results using test genre |
US6570555B1 (en) * | 1998-12-30 | 2003-05-27 | Fuji Xerox Co., Ltd. | Method and apparatus for embodied conversational characters with multimodal input/output in an interface device |
US6574622B1 (en) * | 1998-09-07 | 2003-06-03 | Fuji Xerox Co. Ltd. | Apparatus and method for document retrieval |
US6581066B1 (en) * | 1999-11-29 | 2003-06-17 | Xerox Corporation | Technique enabling end users to create secure command-language-based services dynamically |
Family Cites Families (60)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4798543A (en) | 1983-03-31 | 1989-01-17 | Bell & Howell Company | Interactive training method and system |
US4816994A (en) * | 1984-12-04 | 1989-03-28 | Tektronix, Inc. | Rule acquisition for expert systems |
US4787035A (en) | 1985-10-17 | 1988-11-22 | Westinghouse Electric Corp. | Meta-interpreter |
US4847784A (en) | 1987-07-13 | 1989-07-11 | Teknowledge, Inc. | Knowledge based tutor |
US4867685A (en) | 1987-09-24 | 1989-09-19 | The Trustees Of The College Of Aeronautics | Audio visual instructional system |
US4914590A (en) | 1988-05-18 | 1990-04-03 | Emhart Industries, Inc. | Natural language understanding system |
SE466029B (en) | 1989-03-06 | 1991-12-02 | Ibm Svenska Ab | DEVICE AND PROCEDURE FOR ANALYSIS OF NATURAL LANGUAGES IN A COMPUTER-BASED INFORMATION PROCESSING SYSTEM |
US5035625A (en) | 1989-07-24 | 1991-07-30 | Munson Electronics, Inc. | Computer game teaching method and system |
US5239617A (en) | 1990-01-05 | 1993-08-24 | International Business Machines Corporation | Method and apparatus providing an intelligent help explanation paradigm paralleling computer user activity |
US5265014A (en) | 1990-04-10 | 1993-11-23 | Hewlett-Packard Company | Multi-modal user interface |
US5404295A (en) | 1990-08-16 | 1995-04-04 | Katz; Boris | Method and apparatus for utilizing annotations to facilitate computer retrieval of database material |
US5309359A (en) | 1990-08-16 | 1994-05-03 | Boris Katz | Method and apparatus for generating and utlizing annotations to facilitate computer text retrieval |
US5418717A (en) | 1990-08-27 | 1995-05-23 | Su; Keh-Yih | Multiple score language processing system |
JPH04113385A (en) | 1990-09-03 | 1992-04-14 | Fujitsu Ltd | Remote lecture system |
US5586218A (en) | 1991-03-04 | 1996-12-17 | Inference Corporation | Autonomous learning and reasoning agent |
AU1458492A (en) | 1991-03-04 | 1992-10-06 | Inference Corporation | Case-based reasoning system |
JPH04357549A (en) | 1991-03-07 | 1992-12-10 | Hitachi Ltd | Education system |
JP2804403B2 (en) | 1991-05-16 | 1998-09-24 | インターナショナル・ビジネス・マシーンズ・コーポレイション | Question answering system |
US5301314A (en) | 1991-08-05 | 1994-04-05 | Answer Computer, Inc. | Computer-aided customer support system with bubble-up |
US5265065A (en) | 1991-10-08 | 1993-11-23 | West Publishing Company | Method and apparatus for information retrieval from a database by replacing domain specific stemmed phases in a natural language to create a search query |
US5423032A (en) | 1991-10-31 | 1995-06-06 | International Business Machines Corporation | Method for extracting multi-word technical terms from text |
US5259766A (en) | 1991-12-13 | 1993-11-09 | Educational Testing Service | Method and system for interactive computer science testing, anaylsis and feedback |
US5267865A (en) | 1992-02-11 | 1993-12-07 | John R. Lee | Interactive computer aided natural learning method and apparatus |
WO1993021587A2 (en) | 1992-04-15 | 1993-10-28 | Inference Corporation | Machine learning with a relational database |
GB9209346D0 (en) * | 1992-04-30 | 1992-06-17 | Sharp Kk | Machine translation system |
US5999908A (en) | 1992-08-06 | 1999-12-07 | Abelow; Daniel H. | Customer-based product design module |
JP2973726B2 (en) * | 1992-08-31 | 1999-11-08 | 株式会社日立製作所 | Information processing device |
NZ299101A (en) | 1992-09-04 | 1997-06-24 | Caterpillar Inc | Computer-based document development system: includes text editor and language editor enforcing lexical and grammatical constraints |
US5286036A (en) | 1992-09-08 | 1994-02-15 | Abrasion Engineering Company Limited | Method of playing electronic game, and electronic game |
US5446883A (en) | 1992-10-23 | 1995-08-29 | Answer Systems, Inc. | Method and system for distributed information management and document retrieval |
CA2119397C (en) | 1993-03-19 | 2007-10-02 | Kim E.A. Silverman | Improved automated voice synthesis employing enhanced prosodic treatment of text, spelling of text and rate of annunciation |
US5454106A (en) | 1993-05-17 | 1995-09-26 | International Business Machines Corporation | Database retrieval system using natural language for presenting understood components of an ambiguous query on a user interface |
US5701399A (en) | 1993-06-09 | 1997-12-23 | Inference Corporation | Integration of case-based search engine into help database |
US5519608A (en) | 1993-06-24 | 1996-05-21 | Xerox Corporation | Method for extracting from a text corpus answers to questions stated in natural language by using linguistic analysis and hypothesis generation |
AU7323694A (en) | 1993-07-07 | 1995-02-06 | Inference Corporation | Case-based organizing and querying of a database |
US5495604A (en) | 1993-08-25 | 1996-02-27 | Asymetrix Corporation | Method and apparatus for the modeling and query of database structures using natural language-like constructs |
US5597312A (en) | 1994-05-04 | 1997-01-28 | U S West Technologies, Inc. | Intelligent tutoring method and system |
WO1995035541A1 (en) | 1994-06-22 | 1995-12-28 | Molloy Bruce G | A system and method for representing and retrieving knowledge in an adaptive cognitive network |
US5758257A (en) | 1994-11-29 | 1998-05-26 | Herz; Frederick | System and method for scheduling broadcast of and access to video programs and other data using customer profiles |
US5794050A (en) | 1995-01-04 | 1998-08-11 | Intelligent Text Processing, Inc. | Natural language understanding system |
US5634121A (en) | 1995-05-30 | 1997-05-27 | Lockheed Martin Corporation | System for identifying and linking domain information using a parsing process to identify keywords and phrases |
US5819260A (en) | 1996-01-22 | 1998-10-06 | Lexis-Nexis | Phrase recognition method and apparatus |
US6076088A (en) | 1996-02-09 | 2000-06-13 | Paik; Woojin | Information extraction system and method using concept relation concept (CRC) triples |
US5862325A (en) | 1996-02-29 | 1999-01-19 | Intermind Corporation | Computer-based communication system and method using metadata defining a control structure |
US5797135A (en) | 1996-05-01 | 1998-08-18 | Serviceware, Inc. | Software structure for data delivery on multiple engines |
US6101515A (en) | 1996-05-31 | 2000-08-08 | Oracle Corporation | Learning system for classification of terminology |
US5959543A (en) | 1996-08-22 | 1999-09-28 | Lucent Technologies Inc. | Two-way wireless messaging system with flexible messaging |
US5933531A (en) | 1996-08-23 | 1999-08-03 | International Business Machines Corporation | Verification and correction method and system for optical character recognition |
US5933816A (en) | 1996-10-31 | 1999-08-03 | Citicorp Development Center, Inc. | System and method for delivering financial services |
US5909679A (en) | 1996-11-08 | 1999-06-01 | At&T Corp | Knowledge-based moderator for electronic mail help lists |
EP0841624A1 (en) * | 1996-11-08 | 1998-05-13 | Softmark Limited | Input and output communication in a data processing system |
US5963948A (en) | 1996-11-15 | 1999-10-05 | Shilcrat; Esther Dina | Method for generating a path in an arbitrary physical structure |
US6078914A (en) | 1996-12-09 | 2000-06-20 | Open Text Corporation | Natural language meta-search system and method |
US5963965A (en) | 1997-02-18 | 1999-10-05 | Semio Corporation | Text processing and retrieval system and method |
US5819258A (en) | 1997-03-07 | 1998-10-06 | Digital Equipment Corporation | Method and apparatus for automatically generating hierarchical categories from large document collections |
US5933822A (en) | 1997-07-22 | 1999-08-03 | Microsoft Corporation | Apparatus and methods for an information retrieval system that employs natural language processing of search results to improve overall precision |
US6266664B1 (en) | 1997-10-01 | 2001-07-24 | Rulespace, Inc. | Method for scanning, analyzing and rating digital information content |
US6029043A (en) * | 1998-01-29 | 2000-02-22 | Ho; Chi Fai | Computer-aided group-learning methods and systems |
US6393428B1 (en) | 1998-07-13 | 2002-05-21 | Microsoft Corporation | Natural language information retrieval system |
US6349307B1 (en) | 1998-12-28 | 2002-02-19 | U.S. Philips Corporation | Cooperative topical servers with automatic prefiltering and routing |
-
1999
- 1999-09-01 US US09/387,932 patent/US6498921B1/en not_active Expired - Lifetime
-
2002
- 2002-01-28 US US10/060,120 patent/US20020128818A1/en not_active Abandoned
Patent Citations (87)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4594686A (en) * | 1979-08-30 | 1986-06-10 | Sharp Kabushiki Kaisha | Language interpreter for inflecting words from their uninflected forms |
US4641264A (en) * | 1981-09-04 | 1987-02-03 | Hitachi, Ltd. | Method for automatic translation between natural languages |
US4597057A (en) * | 1981-12-31 | 1986-06-24 | System Development Corporation | System for compressed storage of 8-bit ASCII bytes using coded strings of 4 bit nibbles |
US4586160A (en) * | 1982-04-07 | 1986-04-29 | Tokyo Shibaura Denki Kabushiki Kaisha | Method and apparatus for analyzing the syntactic structure of a sentence |
US4674065A (en) * | 1982-04-30 | 1987-06-16 | International Business Machines Corporation | System for detecting and correcting contextual errors in a text processing system |
US4599691A (en) * | 1982-05-20 | 1986-07-08 | Kokusai Denshin Denwa Co., Ltd. | Tree transformation system in machine translation system |
US4773009A (en) * | 1986-06-06 | 1988-09-20 | Houghton Mifflin Company | Method and apparatus for text analysis |
US5560037A (en) * | 1987-12-28 | 1996-09-24 | Xerox Corporation | Compact hyphenation point data |
US5088048A (en) * | 1988-06-10 | 1992-02-11 | Xerox Corporation | Massively parallel propositional reasoning |
US5438511A (en) * | 1988-10-19 | 1995-08-01 | Xerox Corporation | Disjunctive unification |
US5070478A (en) * | 1988-11-21 | 1991-12-03 | Xerox Corporation | Modifying text data to change features in a region of text |
US5111398A (en) * | 1988-11-21 | 1992-05-05 | Xerox Corporation | Processing natural language text using autonomous punctuational structure |
US5224038A (en) * | 1989-04-05 | 1993-06-29 | Xerox Corporation | Token editor architecture |
US5625773A (en) * | 1989-04-05 | 1997-04-29 | Xerox Corporation | Method of encoding and line breaking text |
US5278980A (en) * | 1991-08-16 | 1994-01-11 | Xerox Corporation | Iterative technique for phrase query formation and an information retrieval system employing same |
US5625554A (en) * | 1992-07-20 | 1997-04-29 | Xerox Corporation | Finite-state transduction of related word forms for text indexing and retrieval |
US5594641A (en) * | 1992-07-20 | 1997-01-14 | Xerox Corporation | Finite-state transduction of related word forms for text indexing and retrieval |
US5598518A (en) * | 1993-03-10 | 1997-01-28 | Fuji Xerox Co., Ltd. | Text editing apparatus for rearranging sentences |
US5638543A (en) * | 1993-06-03 | 1997-06-10 | Xerox Corporation | Method and apparatus for automatic document summarization |
US5696962A (en) * | 1993-06-24 | 1997-12-09 | Xerox Corporation | Method for computerized information retrieval using shallow linguistic analysis |
US5384703A (en) * | 1993-07-02 | 1995-01-24 | Xerox Corporation | Method and apparatus for summarizing documents according to theme |
US5386276A (en) * | 1993-07-12 | 1995-01-31 | Xerox Corporation | Detecting and correcting for low developed mass per unit area |
US5500920A (en) * | 1993-09-23 | 1996-03-19 | Xerox Corporation | Semantic co-occurrence filtering for speech recognition and signal transcription applications |
US6366697B1 (en) * | 1993-10-06 | 2002-04-02 | Xerox Corporation | Rotationally desensitized unistroke handwriting recognition |
US5752021A (en) * | 1994-05-24 | 1998-05-12 | Fuji Xerox Co., Ltd. | Document database management apparatus capable of conversion between retrieval formulae for different schemata |
US5675819A (en) * | 1994-06-16 | 1997-10-07 | Xerox Corporation | Document information retrieval using global word co-occurrence patterns |
US5862321A (en) * | 1994-06-27 | 1999-01-19 | Xerox Corporation | System and method for accessing and distributing electronic documents |
US6144997A (en) * | 1994-06-27 | 2000-11-07 | Xerox Corporation | System and method for accessing and distributing electronic documents |
US5649218A (en) * | 1994-07-19 | 1997-07-15 | Fuji Xerox Co., Ltd. | Document structure retrieval apparatus utilizing partial tag-restored structure |
US5689716A (en) * | 1995-04-14 | 1997-11-18 | Xerox Corporation | Automatic method of generating thematic summaries |
US5745602A (en) * | 1995-05-01 | 1998-04-28 | Xerox Corporation | Automatic method of selecting multi-word key phrases from a document |
US5883986A (en) * | 1995-06-02 | 1999-03-16 | Xerox Corporation | Method and system for automatic transcription correction |
US5831853A (en) * | 1995-06-07 | 1998-11-03 | Xerox Corporation | Automatic construction of digital controllers/device drivers for electro-mechanical systems using component models |
US5778397A (en) * | 1995-06-28 | 1998-07-07 | Xerox Corporation | Automatic method of generating feature probabilities for automatic extracting summarization |
US5918240A (en) * | 1995-06-28 | 1999-06-29 | Xerox Corporation | Automatic method of extracting summarization using feature probabilities |
US5721939A (en) * | 1995-08-03 | 1998-02-24 | Xerox Corporation | Method and apparatus for tokenizing text |
US5870741A (en) * | 1995-10-20 | 1999-02-09 | Fuji Xerox Co., Ltd. | Information management device |
US5727222A (en) * | 1995-12-14 | 1998-03-10 | Xerox Corporation | Method of parsing unification based grammars using disjunctive lazy copy links |
US5892842A (en) * | 1995-12-14 | 1999-04-06 | Xerox Corporation | Automatic method of identifying sentence boundaries in a document image |
US5850476A (en) * | 1995-12-14 | 1998-12-15 | Xerox Corporation | Automatic method of identifying drop words in a document image without performing character recognition |
US5848191A (en) * | 1995-12-14 | 1998-12-08 | Xerox Corporation | Automatic method of generating thematic summaries from a document image without performing character recognition |
US5911140A (en) * | 1995-12-14 | 1999-06-08 | Xerox Corporation | Method of ordering document clusters given some knowledge of user interests |
US5787420A (en) * | 1995-12-14 | 1998-07-28 | Xerox Corporation | Method of ordering document clusters without requiring knowledge of user interests |
US5903860A (en) * | 1996-06-21 | 1999-05-11 | Xerox Corporation | Method of conjoining clauses during unification using opaque clauses |
US5819210A (en) * | 1996-06-21 | 1998-10-06 | Xerox Corporation | Method of lazy contexted copying during unification |
US6064953A (en) * | 1996-06-21 | 2000-05-16 | Xerox Corporation | Method for creating a disjunctive edge graph from subtrees during unification |
US6023760A (en) * | 1996-06-22 | 2000-02-08 | Xerox Corporation | Modifying an input string partitioned in accordance with directionality and length constraints |
US6016516A (en) * | 1996-08-07 | 2000-01-18 | Fuji Xerox Co. Ltd. | Remote procedure processing device used by at least two linked computer systems |
US5944530A (en) * | 1996-08-13 | 1999-08-31 | Ho; Chi Fai | Learning method and system that consider a student's concentration level |
US5905980A (en) * | 1996-10-31 | 1999-05-18 | Fuji Xerox Co., Ltd. | Document processing apparatus, word extracting apparatus, word extracting method and storage medium for storing word extracting program |
US5943669A (en) * | 1996-11-25 | 1999-08-24 | Fuji Xerox Co., Ltd. | Document retrieval device |
US6501937B1 (en) * | 1996-12-02 | 2002-12-31 | Chi Fai Ho | Learning method and system based on questioning |
US6339783B1 (en) * | 1996-12-10 | 2002-01-15 | Fuji Xerox Co., Ltd. | Procedure execution device and procedure execution method |
US6076086A (en) * | 1997-03-17 | 2000-06-13 | Fuji Xerox Co., Ltd. | Associate document retrieving apparatus and storage medium for storing associate document retrieving program |
US6006240A (en) * | 1997-03-31 | 1999-12-21 | Xerox Corporation | Cell identification in table analysis |
US6202064B1 (en) * | 1997-06-20 | 2001-03-13 | Xerox Corporation | Linguistic search system |
US6505150B2 (en) * | 1997-07-02 | 2003-01-07 | Xerox Corporation | Article and method of automatically filtering information retrieval results using test genre |
US6282509B1 (en) * | 1997-11-18 | 2001-08-28 | Fuji Xerox Co., Ltd. | Thesaurus retrieval and synthesis system |
US6128634A (en) * | 1998-01-06 | 2000-10-03 | Fuji Xerox Co., Ltd. | Method and apparatus for facilitating skimming of text |
US6466213B2 (en) * | 1998-02-13 | 2002-10-15 | Xerox Corporation | Method and apparatus for creating personal autonomous avatars |
US5937224A (en) * | 1998-03-05 | 1999-08-10 | Xerox Corporation | Cleaner stress indicator |
US5903796A (en) * | 1998-03-05 | 1999-05-11 | Xerox Corporation | P/R process control patch uniformity analyzer |
US5960228A (en) * | 1998-03-05 | 1999-09-28 | Xerox Corporation | Dirt level early warning system |
US5946521A (en) * | 1998-03-05 | 1999-08-31 | Xerox Corporation | Xerographic xerciser including a hierarchy system for determining part replacement and failure |
US5995775A (en) * | 1998-03-05 | 1999-11-30 | Xerox Corporation | ROS pixel size growth detector |
US6016204A (en) * | 1998-03-05 | 2000-01-18 | Xerox Corporation | Actuator performance indicator |
US6198885B1 (en) * | 1998-03-05 | 2001-03-06 | Xerox Corporation | Non-uniform development indicator |
US6081348A (en) * | 1998-03-05 | 2000-06-27 | Xerox Corporation | Ros beam failure detector |
US6289304B1 (en) * | 1998-03-23 | 2001-09-11 | Xerox Corporation | Text summarization using part-of-speech |
US6321189B1 (en) * | 1998-07-02 | 2001-11-20 | Fuji Xerox Co., Ltd. | Cross-lingual retrieval system and method that utilizes stored pair data in a vector space model to process queries |
US6574622B1 (en) * | 1998-09-07 | 2003-06-03 | Fuji Xerox Co. Ltd. | Apparatus and method for document retrieval |
US6308149B1 (en) * | 1998-12-16 | 2001-10-23 | Xerox Corporation | Grouping words with equivalent substrings by automatic clustering based on suffix relationships |
US6430557B1 (en) * | 1998-12-16 | 2002-08-06 | Xerox Corporation | Identifying a group of words using modified query words obtained from successive suffix relationships |
US6493663B1 (en) * | 1998-12-17 | 2002-12-10 | Fuji Xerox Co., Ltd. | Document summarizing apparatus, document summarizing method and recording medium carrying a document summarizing program |
US6321372B1 (en) * | 1998-12-23 | 2001-11-20 | Xerox Corporation | Executable for requesting a linguistic service |
US6167369A (en) * | 1998-12-23 | 2000-12-26 | Xerox Company | Automatic language identification using both N-gram and word information |
US6269189B1 (en) * | 1998-12-29 | 2001-07-31 | Xerox Corporation | Finding selected character strings in text and providing information relating to the selected character strings |
US6570555B1 (en) * | 1998-12-30 | 2003-05-27 | Fuji Xerox Co., Ltd. | Method and apparatus for embodied conversational characters with multimodal input/output in an interface device |
US6470334B1 (en) * | 1999-01-07 | 2002-10-22 | Fuji Xerox Co., Ltd. | Document retrieval apparatus |
US6321191B1 (en) * | 1999-01-19 | 2001-11-20 | Fuji Xerox Co., Ltd. | Related sentence retrieval system having a plurality of cross-lingual retrieving units that pairs similar sentences based on extracted independent words |
US6389435B1 (en) * | 1999-02-05 | 2002-05-14 | Fuji Xerox, Co, Ltd. | Method and system for copying a freeform digital ink mark on an object to a related object |
US6446035B1 (en) * | 1999-05-05 | 2002-09-03 | Xerox Corporation | Finding groups of people based on linguistically analyzable content of resources accessed |
US6498921B1 (en) * | 1999-09-01 | 2002-12-24 | Chi Fai Ho | Method and system to answer a natural-language question |
US6393389B1 (en) * | 1999-09-23 | 2002-05-21 | Xerox Corporation | Using ranked translation choices to obtain sequences indicating meaning of multi-token expressions |
US6411962B1 (en) * | 1999-11-29 | 2002-06-25 | Xerox Corporation | Systems and methods for organizing text |
US6581066B1 (en) * | 1999-11-29 | 2003-06-17 | Xerox Corporation | Technique enabling end users to create secure command-language-based services dynamically |
US6473729B1 (en) * | 1999-12-20 | 2002-10-29 | Xerox Corporation | Word phrase translation using a phrase index |
Cited By (43)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060167678A1 (en) * | 2003-03-14 | 2006-07-27 | Ford W R | Surface structure generation |
US7599831B2 (en) | 2003-03-14 | 2009-10-06 | Sonum Technologies, Inc. | Multi-stage pattern reduction for natural language processing |
US20050071216A1 (en) * | 2003-09-30 | 2005-03-31 | Microsoft Corporation | Interactive network guide |
US7580835B2 (en) * | 2003-12-25 | 2009-08-25 | Kabushiki Kaisha Toshiba | Question-answering method, system, and program for answering question input by speech |
US20050143999A1 (en) * | 2003-12-25 | 2005-06-30 | Yumi Ichimura | Question-answering method, system, and program for answering question input by speech |
US20060004724A1 (en) * | 2004-06-03 | 2006-01-05 | Oki Electric Industry Co., Ltd. | Information-processing system, information-processing method and information-processing program |
US8224802B2 (en) | 2005-03-31 | 2012-07-17 | Google Inc. | User interface for facts query engine with snippets from information sources that include query terms and answer terms |
US8650175B2 (en) | 2005-03-31 | 2014-02-11 | Google Inc. | User interface for facts query engine with snippets from information sources that include query terms and answer terms |
US7953720B1 (en) | 2005-03-31 | 2011-05-31 | Google Inc. | Selecting the best answer to a fact query from among a set of potential answers |
US8239394B1 (en) | 2005-03-31 | 2012-08-07 | Google Inc. | Bloom filters for query simulation |
US8065290B2 (en) | 2005-03-31 | 2011-11-22 | Google Inc. | User interface for facts query engine with snippets from information sources that include query terms and answer terms |
US20070067155A1 (en) * | 2005-09-20 | 2007-03-22 | Sonum Technologies, Inc. | Surface structure generation |
US9530229B2 (en) | 2006-01-27 | 2016-12-27 | Google Inc. | Data object visualization using graphs |
US7925676B2 (en) | 2006-01-27 | 2011-04-12 | Google Inc. | Data object visualization using maps |
US8954426B2 (en) | 2006-02-17 | 2015-02-10 | Google Inc. | Query language |
US20070198499A1 (en) * | 2006-02-17 | 2007-08-23 | Tom Ritchford | Annotation framework |
US8055674B2 (en) | 2006-02-17 | 2011-11-08 | Google Inc. | Annotation framework |
US9159316B2 (en) * | 2006-04-03 | 2015-10-13 | Google Inc. | Automatic language model update |
US20130246065A1 (en) * | 2006-04-03 | 2013-09-19 | Google Inc. | Automatic Language Model Update |
US10410627B2 (en) | 2006-04-03 | 2019-09-10 | Google Llc | Automatic language model update |
US9953636B2 (en) | 2006-04-03 | 2018-04-24 | Google Llc | Automatic language model update |
US8954412B1 (en) | 2006-09-28 | 2015-02-10 | Google Inc. | Corroborating facts in electronic documents |
US9785686B2 (en) | 2006-09-28 | 2017-10-10 | Google Inc. | Corroborating facts in electronic documents |
US9892132B2 (en) | 2007-03-14 | 2018-02-13 | Google Llc | Determining geographic locations for place names in a fact repository |
US10459955B1 (en) | 2007-03-14 | 2019-10-29 | Google Llc | Determining geographic locations for place names |
US8239751B1 (en) * | 2007-05-16 | 2012-08-07 | Google Inc. | Data from web documents in a spreadsheet |
US7809664B2 (en) | 2007-12-21 | 2010-10-05 | Yahoo! Inc. | Automated learning from a question and answering network of humans |
US20090162824A1 (en) * | 2007-12-21 | 2009-06-25 | Heck Larry P | Automated learning from a question and answering network of humans |
US9087059B2 (en) | 2009-08-07 | 2015-07-21 | Google Inc. | User interface for presenting search results for multiple regions of a visual query |
US9135277B2 (en) | 2009-08-07 | 2015-09-15 | Google Inc. | Architecture for responding to a visual query |
US10534808B2 (en) | 2009-08-07 | 2020-01-14 | Google Llc | Architecture for responding to visual query |
US20130196305A1 (en) * | 2012-01-30 | 2013-08-01 | International Business Machines Corporation | Method and apparatus for generating questions |
US9484034B2 (en) | 2014-02-13 | 2016-11-01 | Kabushiki Kaisha Toshiba | Voice conversation support apparatus, voice conversation support method, and computer readable medium |
US11392778B2 (en) * | 2014-12-29 | 2022-07-19 | Paypal, Inc. | Use of statistical flow data for machine translations between different languages |
US10102275B2 (en) | 2015-05-27 | 2018-10-16 | International Business Machines Corporation | User interface for a query answering system |
US10157174B2 (en) * | 2015-05-27 | 2018-12-18 | International Business Machines Corporation | Utilizing a dialectical model in a question answering system |
US20170255609A1 (en) * | 2015-05-27 | 2017-09-07 | International Business Machines Corporation | Utilizing a dialectical model in a question answering system |
US20160350279A1 (en) * | 2015-05-27 | 2016-12-01 | International Business Machines Corporation | Utilizing a dialectical model in a question answering system |
US9727552B2 (en) * | 2015-05-27 | 2017-08-08 | International Business Machines Corporation | Utilizing a dialectical model in a question answering system |
US10942958B2 (en) | 2015-05-27 | 2021-03-09 | International Business Machines Corporation | User interface for a query answering system |
US11030227B2 (en) | 2015-12-11 | 2021-06-08 | International Business Machines Corporation | Discrepancy handler for document ingestion into a corpus for a cognitive computing system |
US11074286B2 (en) | 2016-01-12 | 2021-07-27 | International Business Machines Corporation | Automated curation of documents in a corpus for a cognitive computing system |
US11308143B2 (en) | 2016-01-12 | 2022-04-19 | International Business Machines Corporation | Discrepancy curator for documents in a corpus of a cognitive computing system |
Also Published As
Publication number | Publication date |
---|---|
US6498921B1 (en) | 2002-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6498921B1 (en) | Method and system to answer a natural-language question | |
JP6414956B2 (en) | Question generating device and computer program | |
US6850934B2 (en) | Adaptive search engine query | |
US6829603B1 (en) | System, method and program product for interactive natural dialog | |
JP4398098B2 (en) | Glamor template query system | |
US6999916B2 (en) | Method and apparatus for integrated, user-directed web site text translation | |
US9323848B2 (en) | Search system using search subdomain and hints to subdomains in search query statements and sponsored results on a subdomain-by-subdomain basis | |
US7587389B2 (en) | Question answering system, data search method, and computer program | |
US6571240B1 (en) | Information processing for searching categorizing information in a document based on a categorization hierarchy and extracted phrases | |
US7403938B2 (en) | Natural language query processing | |
US7089236B1 (en) | Search engine interface | |
US7526474B2 (en) | Question answering system, data search method, and computer program | |
Staab et al. | GETESS—searching the web exploiting german texts | |
US10409803B1 (en) | Domain name generation and searching using unigram queries | |
US10380248B1 (en) | Acronym identification in domain names | |
US7668859B2 (en) | Method and system for enhanced web searching | |
US11256770B2 (en) | Data-driven online business name generator | |
US20200351241A1 (en) | Data-driven online domain name generator | |
Kumar et al. | A query answering system for E-learning Hindi documents | |
CN115618087B (en) | Method and device for storing, searching and displaying multilingual translation corpus | |
JPH10207904A (en) | System and method for retrieving knowledge information | |
JP2012243130A (en) | Information retrieval device, method and program | |
JP2022165715A (en) | Information searching program, information searching method, and information searching apparatus | |
US20200349209A1 (en) | Data-driven online social media handle generator | |
US8676790B1 (en) | Methods and systems for improving search rankings using advertising data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: HASTUR LIMITED LLC, DELAWARE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MINDFABRIC HOLDINGS, LLC;REEL/FRAME:018951/0824 Effective date: 20060906 |
|
AS | Assignment |
Owner name: PROFESSORQ, INC., CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:IP LEARN, INC.;REEL/FRAME:019550/0255 Effective date: 20000126 Owner name: IP LEARN, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:IPLEARN, LLC;REEL/FRAME:019550/0182 Effective date: 20000306 Owner name: LINDNER, ROBERT D., JR., OHIO Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MINDFABRIC, INC.;REEL/FRAME:019553/0474 Effective date: 20061128 Owner name: MINDFABRIC HOLDINGS, LLC, OHIO Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ROBERT D. LINDNER, JR.;REEL/FRAME:019553/0525 Effective date: 20061010 |
|
AS | Assignment |
Owner name: IPLEARN, LLC, CALIFORNIA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE EXECUTION DATE OF THE ASSIGNMENT AS BEING 03/05/2000 PREVIOUSLY RECORDED ON REEL 013530 FRAME 0995;ASSIGNOR:TONG, PETER P.;REEL/FRAME:019559/0088 Effective date: 20061120 |
|
AS | Assignment |
Owner name: IPLEARN, LLC, CALIFORNIA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE CLERICAL ERROR IN THE SPELLING OF THE INVENTOR'S NAME, CHI FAI HO PREVIOUSLY RECORDED ON REEL 011806 FRAME 0487;ASSIGNOR:HO, CHI FAI;REEL/FRAME:019562/0129 Effective date: 20061117 Owner name: MINDFABRIC, INC., CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:PROFESSORQ, INC.;REEL/FRAME:019562/0260 Effective date: 20011220 |
|
AS | Assignment |
Owner name: HANGER SOLUTIONS, LLC, GEORGIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTELLECTUAL VENTURES ASSETS 161 LLC;REEL/FRAME:052159/0509 Effective date: 20191206 |
|
AS | Assignment |
Owner name: INTELLECTUAL VENTURES ASSETS 161 LLC, DELAWARE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BENHOV GMBH, LLC;REEL/FRAME:051856/0776 Effective date: 20191126 |