WO2000029978A1 - Universal translation method - Google Patents
Universal translation method Download PDFInfo
- Publication number
- WO2000029978A1 WO2000029978A1 PCT/US1999/027364 US9927364W WO0029978A1 WO 2000029978 A1 WO2000029978 A1 WO 2000029978A1 US 9927364 W US9927364 W US 9927364W WO 0029978 A1 WO0029978 A1 WO 0029978A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- source
- target
- language
- triplets
- triplet
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/55—Rule-based translation
Definitions
- the present invention relates to machine translation and, more particularly, to a universal translation system applicable for transforming signals that embody knowledge according to a knowledge representation, such as a natural language.
- U.S. Patent No. 4,706,212 software routines are hard-coded to translate sentences in a source language to sentences in a target language.
- the complexity of the grammar of the source and target languages is handled by various ad-hoc, hard-coded logic.
- U.S. Patent No. 4,706.212 discloses logic for recognizing some grammatical constructions in English as a source language and outputting a Russian construction.
- the logic devised for recognizing and translating these source grammatical constructions is tightly coupled to a particular source language.
- most of the subroutines coded to handle English source construction are utterly inapplicable for another language such as Chinese.
- a source signal embodying knowledge is decomposed into a simple and regular internal representation.
- This internal representation is then transformed into another internal representation from which a target signal is constructed.
- the complexity of language is appropriately localized within rules for decomposing the source signal into the internal representation and transforming the internal representation into another internal representation.
- source signal decomposition and target signal constructions are facilitated by look ups into a universal dictionary.
- extending and improving such a language translation system involves updating the universal dictionary, the decomposition rules, and the mapping rules, thereby avoiding modification of hard-coded logic and internal data structures.
- one aspect of the invention relates to a method and a computer- readable medium bearing instructions for translating a source signal embodying information according to a source language into a target signal embodying information according to target language.
- the methodology involves analyzing the source signal to produce a first internal representation of epistemic instances corresponding to the information embodied in the source signal.
- the epistemic instances are fundamental semantic structures expressing a transformation of two objects or objective grammatical forms.
- the first internal representation is transformed into a second internal representation of epistemic instances according to the target language, and the target signal is constructed based on the second internal representation.
- the source language and the target language may be any of a natural language, a computer language, formatting conventions, and mathematical expressions.
- the source signal and the target signal can be realized as digital signals representing text, acoustic signals representing speech, optical signals representing characters, and as any other analog or digital signal.
- the described methodology is also applicable to transforming a source signal embodying information according a knowledge representation relating to a knowledge discipline, for example, physics and engineering.
- a method and computer-readable medium bearing instructions for translating a source signal embodying information according to a source language into a target signal embodying information according to target language involve storing related dictionary entries in a computer-readable medium.
- Each related dictionary entry includes a source word form, a source grammatical form, a corresponding target word form, and a target grammatical form for the target word form.
- the grammatical form in some embodiments relates to a sub-grammatical form for specifying the morphology of a word form including grammatical inflection and auxiliaries.
- the source signal is analyzed to produce a first internal representation of the information embodied in the source signal based on the dictionary entries.
- the first internal representation is transformed into a second internal representation according to the second internal representation, from which the target signal is constructed.
- the dictionary entries properly localize much of the complexity language. Word forms in the dictionary entries may correspond to one or multiple lexical words interspersed throughout a sentence.
- the source signal is analyzed by applying decomposition rules that describe how to partition the word forms in the source signal into three data sets constituting a triplet.
- decomposition rules that describe how to partition the word forms in the source signal into three data sets constituting a triplet.
- One advantage of a triplet data structure is that it can provide a straightforward representation of an epistemic instance.
- at least some of the triplets in the first internal representation are mapped to produce the second internal representation by accessing a sequence of mapping rules.
- the mapping rules describe a correspondence between a source language triplet and a corresponding target language triplet.
- FIG 1 schematically depicts a computer system upon which an embodiment of the present invention can be implemented;
- FIG. 2 schematically depicts components of a universal language translation system:
- FIG. 3(a) is a flowchart showing the operation of a universal language translation system;
- FIG. 3(b) is a flowchart showing the operation of determining a grammatical form for a word
- FIG. 4(a) depicts an initial split tree before mapping
- FIG. 4(b) depicts the split tree during mapping
- FIG. 4(c) depicts the split tree at another point during mapping
- FIG. 4(d) depicts the split tree at still another point during mapping
- FIG. 4(e) depicts the split tree at yet another point during mapping
- FIG. 4(f) depicts the split tree after mapping.
- the present invention stems from the realization that there is a common, regular model for all languages and indeed any knowledge representation.
- This common model is referred to as a "univers grammar.”
- a universal grammar differs from an interlingua, because a universal grammar presents a simple, regular semantic construction of information, while an interlingua is an eclectic conglomeration of grammatical and syntactical surface features of various human languages.
- a universal grammar is described in more detail in U.S. Application Serial No. 09/033.676.
- An epistemic instance which underlies all moments of a being ' s consciousness and perceptions, is a semantic structure of the meaning of any moment of any language.
- an epistemic instance expresses a transformation of two objects.
- the transformation is referred to herein as the " metaverb” and usually corresponds to lexical objects in a human language involving actions or relationships, such as verbs, prepositions, and conjunctions.
- the objects are referred to herein as "metanouns” and usually correspond to lexical objects involving things or concepts as nouns, pronouns, determiners, and adjectives.
- Lexical objects include words, phrases, clauses, sentences, grammatical segments, textual ideas, acoustic phones and phonemes, character strokes of alphabetic letters and Chinese characters, and any other component of meaning.
- Many metaverbs and metanouns can be further decomposed into one or more epistemic instances, expressing a transformation of objects.
- the universal grammar provides the necessary direction for properly localizing the complexity of language. Since linguistic utterances have a simple, regular underlying structure, it follows that the complexity inherent in human language must located elsewhere. More specifically, a universal dictionary is provided for handling the different shades of meaning and grammatical functions each word has, a sequence of split (or decomposition) rules is provided for breaking down a word stream in a decomposition of epistemic instances, and a sequence of mapping rules is provided for mapping the epistemic instances relating to moments of the source language into the epistemic instances relating to moments of the target language. Localizing the complexity within a universal dictionary, split rules, mapping rules, and reconstruction rules allows linguists who are not computer programmers to easily upgrade, extend, and even tweak the language translation system to produce an extensible, reliable, high-quality language translation system.
- FIG. 1 is a block diagram that illustrates a computer system 100 upon which an embodiment of the invention may be implemented.
- Computer system 100 includes a bus 102 or other communication mechanism for communicating information, and a processor 104 coupled with bus 102 for processing information.
- Computer system 100 also includes a main memory 106. such as a random access memory (RAM) or other dynamic storage device, coupled to bus 102 for storing information and instructions to be executed by processor 104.
- Main memory 106 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 104.
- Computer system 100 further includes a read only memory (ROM) 108 or other static storage device coupled to bus 102 for storing static information and instructions for processor 104.
- ROM read only memory
- a storage device 1 10.
- Computer system 100 may be coupled via bus 102 to a display 1 12. such as a cathode ray tube (CRT), for displaying information to a computer user.
- cursor control 1 16 such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 104 and for controlling cursor movement on display 1 12.
- This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane.
- the invention is related to the use of computer system 100 for language translation.
- language translation is provided by computer system 100 in response to processor 104 executing one or more sequences of one or more instructions contained in main memory 106.
- Such instructions may be read into main memory 106 from another computer-readable medium, such as storage device 1 10.
- Execution of the sequences of instructions contained in main memory 106 causes processor 104 to perform the process steps described herein.
- processors in a multiprocessing arrangement may also be employed to execute the sequences of instructions contained in main memory 106.
- hard- wired circuitry may be used in place of or in combination with software instructions to implement the invention.
- embodiments of the invention are not limited to any specific combination of hardware circuitry and software.
- Non-volatile media include, for example, optical or magnetic disks, such as storage device 1 10.
- Volatile media include dynamic memory, such as main memory 106.
- Transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise bus 102. Transmission media can also take the form of acoustic or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications.
- RF radio frequency
- IR infrared
- Computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM. DVD. any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM. a PROM, and EPROM. a FLASH- EPROM, any other memory chip or cartridge, a carrier wave as described hereinafter, or any other medium from which a computer can read.
- Various forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to processor 104 for execution.
- the instructions may initially be borne on a magnetic disk of a remote computer.
- the remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem.
- a modem local to computer system 100 can receive the data on the telephone line and use an infrared transmitter to convert the data to an infrared signal.
- An infrared detector coupled to bus 102 can receive the data carried in the infrared signal and place the data on bus 102.
- Bus 102 carries the data to main memory 106. from which processor 104 retrieves and executes the instructions.
- the instructions received by main memory 106 may optionally be stored on storage device 1 10 either before or after execution by processor 104.
- Computer system 100 also includes a communication interface 1 18 coupled to bus 102.
- Communication interface 1 18 provides a two-way data communication coupling to a network link 120 that is connected to a local network 122.
- communication interface 1 18 may be an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of telephone line.
- ISDN integrated services digital network
- communication interface 1 18 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN.
- LAN local area network
- Wireless links may also be implemented.
- communication interface 1 18 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
- Network link 120 typically provides data communication through one or more networks to other data devices.
- network link 120 may provide a connection through local network 122 to a host computer 124 or to data equipment operated by an Internet Service Provider (ISP) 126.
- ISP 126 in turn provides data communication services through the worldwide packet data communication network, now commonly referred to as the " Internet" 128.
- Internet 128 uses electrical, electromagnetic or optical signals that carry digital data streams.
- the signals through the various networks and the signals on network link 120 and through communication interface 1 18, which carry the digital data to and from computer system 100, are exemplary forms of carrier waves transporting the information.
- Computer system 100 can send messages and receive data, including program code, through the network(s), network link 120, and communication interface 1 18.
- a server 130 might transmit a requested code for an application program through Internet 128.
- one such downloaded application provides for language translation as described herein.
- the received code may be executed by processor 104 as it is received, and or stored in storage device 1 10, or other non- volatile storage for later execution.
- computer system 100 may obtain application code in the form of a carrier wave.
- embodiments of the present invention are not limited to electronic computing machines, but may also be implemented on optical, biological, and quantum-state computing devices or any combination thereof as these devices become practical in the future.
- the present invention may be implemented by a suitably constructed android such as what is disclosed in the co-pending patent application. U.S. Serial No. 08/847,230.
- FIG. 2 is a schematic diagram of one embodiment of a translation system.
- the translation system comprises a translation engine 200 which is preferably implemented on a computer system as described hereinabove.
- the translation engine 200 includes three modules: a word stream analyzer 202 for decomposing a word stream in the source signal into an internal representation, a mapping unit 204 for transforming the internal representation, and a word stream construction module 206 for converting the transformed internal representation into a target signal.
- a preprocessor 210 and a postprocessor 220 are provided to accommodate the conversion of acoustic, optical, tactile, and other sensory media into " word forms " in the translation engine's preferred digital medium.
- the preprocessor 210 and postprocessor 220 may be implemented by several techniques, such as standard speech recognition and standard optical character recognition, by another instantiation of a suitably configured translation engine as described in detail hereinafter, or by any combination of such techniques.
- the translation engine 220 is preferably configured by linguists with a data-driven programming process implemented in a linguist interface module 230.
- the linguist interface module 230 provides a graphical user interface as a front end to enable a linguist or other language expert to enter, correct, and update entries in the sequence of split rules 232, mapping rules 234, and the universal dictionary 236.
- the universal dictionary 236 contains related entries for words in both the source and target languages. TABLE 1 illustrates some entries in one implementation of the universal dictionary 236. Corresponding words in the universal dictionary are identified by a common key value. For example, the English word " book” , the Chinese word “ sh ⁇ ” , and the Italian word “libro” all have the same key value. Furthermore, each of these words have a grammatical form code (GF Code) of R0 for noun.
- GF Code grammatical form code
- the same word form may be present in more than one entry, in which case the word is semantically or grammatically ambiguous.
- the English verb " read” is ambiguous, because it can correspond to the intransitive Chinese verb " d ⁇ shi (GF Code H2) as in “ I read " or to the transitive Chinese verb "yuelan” (GF Code HI) as in “ I read the book.”
- GF Code H2 intransitive Chinese verb
- GF Code HI g., GF Code HI
- the grammatical form code (GF Code) identifies what functional part of speech the word form belongs to. For example, a GF Code of HI specifies a transitive verb and a GF code of H2 specifies an intransitive verb.
- the grammatical forms will be later used within the word stream analyzer 202 for decomposing the incoming word stream.
- TABLE 2 lists exemplary grammatical form codes, in which related grammatical form codes share a common prefix, thereby allowing for wildcard matching of grammatical forms.
- special word formations are also identified.
- a special word formation is a group of individual words that semantically or grammatically act together as one.
- One way to identify a special word formation is to populate the universal dictionary 236 with an entry for one of the words of the word formation in order to trigger an ambiguity, thereby causing an ambiguity resolution routine to be executed. Executing the ambiguity resolution routines examines other word forms in the word stream to determine whether there is a special word formation.
- Some examples of special word formations include abbreviations, acronyms, words with apostrophes, proper nouns, non-translatable words (e.g.
- a sub-grammatical form is a specialization of a grammatical form that further specifies the morphology or inflection of the word form appropriate to the grammatical form.
- a sub-grammatical form for a Latin adjective would be a combination of its case, number, and gender, for example nominative feminine singular.
- Sub-grammatical forms for a particular word form can be stored in a matrix form, wherein the columns correspond to verb tenses/voices/moods and noun cases, and the rows correspond to verb persons/numbers and noun genders/numbers/articulations.
- Sub-grammatical forms can also be identified from a group of word forms, such a verb and its auxiliaries.
- the mapping rules 234 specify how to transform the internal representation suitable for a source language into an internal representation suitable for a target language.
- TABLE 3 depicts exemplary mapping rules that are used to transform an English prepositional phrase into a Chinese prepositional phrase among other transformations.
- an adjectival prepositional phrase in English of the form " X prep. Y” corresponds the Chinese prepositional phrase " Y prep, de X.”
- the first mapping rule states that the left and right metanouns. labeled -1 and +1 respectively, are swapped, and the second mapping rule states that the Chinese word "Je” is appended to the metaverb.
- Another mapping rule from English to Chinese is deletion of definite articles (GF Code PI ), since Chinese lacks definite articles.
- GF Code H2 since the transitive verb comes in the same place in Chinese as in English, the mapping rule specifies a null transformation.
- the Source and Target fields indicate the source language and the target language respectively.
- the GF Code indicates the grammatical form of the record set, which can be a metaverb or a metanoun.
- the Action field specifies the action to take: " Combine” for combining two word forms into one, " Delete " for deleting a word from a record set, " Move” for moving a word form from one record set to another, " Separate” for separating a word form into two or more word forms, "Add” for adding a word form to a record set, and " Swap " for swapping the positions of two record sets.
- the Set A and the Set B arguments are used in conjunction with the Action field as appropriate and specify the particular result set used by the Action field: -1 for left the metanoun. 0 for the metaverb, and +1 for the right metanoun.
- the mapping rules 234 thus provide a powerful mechanism for handling and translating grammatical constructs.
- the split rules 232 specify how to decompose a grammatical tagged word stream into a " split tree.
- a split tree is hierarchical arrangement of triplets, wherein each triplet partitions one or more word forms into three data sets. The three data sets correspond to the left metanoun. the metaverb. and the right metanoun. respectively, of an epistemic instance. Since the arrangement is hierarchical, the word forms of the metanoun may be partitioned yet again into two metanouns and a metaverb. Thus, a lower-level triplet partitions the word forms embedded in a data set of a higher-level triplet, and the top-level triplet partitions the words of the source signal.
- a split tree using relational database constructs is described in more detail hereinafter.
- the Language field indicates for which language the split rule is appropriate.
- the Sequence field provides an ordering of the split rules, generally from the character and word composition level, to the formatting level, to the paragraph level, to the sentence level, to the clause level, and down to the phrase and word level.
- the Package Name identifies an arrangement of instructions that are configured to identify whether a particular split is appropriate and flags which word forms as belonging to the metaverb (record set 0) of the split.
- SENT_SVO is a package for identifying and splitting subject- verb-object sentences and PREP_POM_NP for identifying and splitting prepositional phrases that are postmodifiers to noun phrases.
- the Split Type field specifies how to perform the split, generally by identifying which word forms that are to be put in the metaverb record set. For example, split type 1 indicates to put only the selected word form in the metaverb record set, split type 3 is for null-metaverb. and split type 4 is for metaverb having more than one word forms, such as a verb and the adverbs that modify it. The remaining word forms, generally to the right and left of the metaverb, are put into the -1 and +1 record sets, respectively, although a special purpose split type may be devised to handle a particularly exotic source language construct.
- record set 0 corresponding to the metaverb, is tagged with a node label indicating the type of split, e.g. SENT_SVO.
- noun phrase [DET+PRM+HN+POM] types including subject, direct object, indirect object, subject predicative, object predicative, complement of a preposition, premodifier of a noun or noun phrase, vocative, adverbial.
- premodifier of an adjective premodifier of a preposition, premodifier of an adverb, postmodifier of a noun, and postmodifier of an adjective;
- adverb phrase [PRM+ADV+POM] types including premodifier of an adjective, and premodifier of an adverb, adverbial, subject predicative, premodifier of a preposition, premodifier of a pronoun, premodifier of a determiner, premodifier of a numeral, premodifier of a noun phrase, postmodifier of a noun phrase. postmodifier of an adjective or adverb, subject predicative, object predicative. and complement of a preposition; and • prepositional phrase [PFN+PREP+PRCMP] types including noun phrase as complement, -ing participle clause as complement. w ⁇ -clause as complement.
- adverb as complement
- adjective as complement
- postmodifier of a noun postmodifier of an adjective
- subject predicative object predicative
- adverbial and complement of a verb
- One way to facilitate the entry of special word forms and sub-grammatical forms is to establish a word construction table (not shown), which allows for groups of word forms to be specified.
- the word construction table can also include positional information to help linguists in one embodiment to write the appropriate split rules 232. mapping rules 234. and entries in the universal dictionary 236 for these special groups of words.
- This positional information may include: any allowable word position, same as the English position, immediately after the keyword, immediately before the keyword, any where after the key word, separated by a word or grammatical form, in combination, at the end of the sentence, and at the beginning of the sentence.
- some of the split rules 232, mapping rules 234, and entries in the universal dictionary 236 can be automatically generated from the word construction.
- special word formations which map multiple word constructions in one language to a single unit in another language, such as idioms, can be handled.
- TABLE 5 illustrates a portion of an exemplary word construction, set up for the verb phrase " have been running," where position code ⁇ A ⁇ means any allowable position, position code ⁇ B ⁇ means before the keyword and separated by an adverb.
- Step 300 is a preprocessing step that receives a source signal as input in one form, such as a digital signal representing text in a source language, an acoustic signal representing speech in a source language, and an optical signal representing characters in the source language.
- This preprocessing step 300 may be performed by standard speech recognition or optical character recognition implementations.
- the preprocessing functionality is handled by another instantiation of the translation engine, wherein the ancillary data structures are appropriately populated.
- the acoustic wave forms or " phones" are stored in the universal dictionary, split rules are devised to recognize phrase, word, and segment boundaries among the phones, and mapping rules are formulated to translate the phones into textual words, for example into ASCII and Unicode.
- the phonemicization of aural speech sounds into recognizable phonemes and then into words is fundamentally a grammatical process
- another embodiment of the universal translation system operating according to the principles of a universal grammar, is an ideal choice for speech recognition.
- the preprocessing and postprocessing stages can be implemented by embodiments of the universal translation system.
- the output of preprocessing in step 300 is a sequence of word forms of the input speech text that are embodied in the source signal.
- This sequence of word forms constitutes a " record set" .
- a person may utter the sentence " I have read the book under the table” into a microphone.
- This acoustic signal, the person ' s utterance is converted by a microphone into analog electric signals.
- the preprocessor module 210 is typically implemented on a digital computer system, the analog electric signals are converted by an analog-to-digital converter to produce a digital signal embodiment of the person's utterances.
- a result set 400 illustrated in FIG. 4(a), is produced.
- the record set 400 comprises eight rows of a table, one row for each word embodied in the source signal.
- each word in the record set 400 is successively visited
- FIG. 3(b) illustrates one technique for determining the grammatical word code.
- the word form under consideration is looked up in the universal dictionary 236 (step 321 ).
- the number of entries returned from the universal dictionary 236 lookup determines how the execution will branch (step 323). If there are no entries in the universal dictionary 236 for the word form, then the grammatical form is established for the word form as a proper noun (step 325). In the working example of " I have read the book under the table," no word form is a proper noun.
- step 329 the grammatical form within the entry of the universal dictionary 236 for the word form is established.
- the pronoun " I" has exactly one entry (see TABLE 1 ) and therefore the grammatical form of SI for personal pronoun is established for the source word form " I.”
- this example is for purposes of illustration and will probably not reflect the state of an actual universal dictionary 236.
- useful embodiments of universal dictionary 236 will include a noun entry for every word to handle self-referential words, such as the word " I" in the sentence, "The word T is a pronoun. "
- the universal dictionary includes Japanese, then there would a plurality of entries for the personal pronoun "I.”
- a word resolution module which is an arrangement of instructions such as a subroutine or and ID package, is executed (step 327) to decide which among the various entries for the word " read " is best.
- the ID package can perform any effectual technique for choosing one of the meanings of the facially ambiguous word form, including inspecting other words in the same context, use of statistical techniques, and even spawning an invocation of the word stream analyzer 202 and the mapping unit 204. If the ID package is unable to disambiguate the word form, then one of the entries will be picked as a default. In the exemplary sentence, the transitive meaning corresponding to the Chinese word yuelan. detectable on account of the direct object noun phrase "the book under the table " , would be selected. Accordingly, the grammatical form HI for transitive verb would be established for the word form (step 329).
- step 330 is the next stage performed by the word stream analyzer 202. More specifically, step 330 iterates over the sequence of split rules 232. For each of the split rules 232. the record set is split according to the split rule if the split rule matches the word forms and grammatical forms in the record set (step 340). In the example, split rule 1 100 of TABLE 4 matches against record set 400. Because record set 400 is a simple sentence in subject- verb-object order. Accordingly, split rule 1 10 causes record set 400 to be partitioned, that is.
- record set 410 containing the pronoun "I” and corresponding to a metanoun as subject in this epistemic instance
- record set 412 with the word forms "have” and “ read” as the metaverb
- the direct object "the book on the table” in a record set 414 as the right metanoun. If adverbs were present, they would go in the metaverb record set 412.
- split rule 1235 of TABLE 4 will eventually match record set 414 and cause the record set 414 to be decomposed into three data sets.
- the -1 record set is record set 420 and contains " the book" as the left metanoun.
- the metaverb is handled in the 0 record set 422 and includes the preposition "on. " and the right metanoun in the +1 record set 424 containing " the table.”
- record set 420 and record set 424 are further decomposed into triplet 430. 432. and 424 and triplet 440. 442, and 444. respectively.
- the split tree of record set 400 is implemented in a table on a relational database system. More specifically, each record set is identified by its own key in the initial data set. a level of decomposition, the particular split set (-1 , 0, or + 1 ), and the key of the word form to the universal dictionary 236. For example. TABLE 6 illustrates any exemplary split table corresponding to the split table of FIG. 4(a). as implemented by a relational database table, with the actual source word form substituted for the universal dictionary 236 key for clarity.
- FIG. 4(a) and TABLE 6 illustrate a split table holding an actual source language word form, such as " I" , in each record.
- the word form is replaced within the split tree by the appropriate key to the universal dictionary 234 entry, facilitating a direct access to the target language word form.
- FIG. 4(b) depicts a more compact schematic of the same split tree, but with elimination of visually redundant elements.
- mapping unit 204 the next step, which is performed by mapping unit 204. is to apply the mapping rules (step 350). More specifically, step 350 iterates over the sequence of mapping rules 234. For each of the mapping rules 234. the record set is mapped according to the mapping rule if the mapping rule matches with any of the node labels, word forms, and grammatical forms in the record set (step 360).
- mapping rule that deletes definite articles as in TABLE 3
- mapping rules can be sequentially sequence similarly to the sequencing of the split rules so that they may execute in a predetermined order. Sequencing mapping rules help to alleviate the implementation of the universal translation system, for example, by placing swaps last.
- the triplet whose metaverb is in record set 430, 432, and 434 is transformed to produce record sets 450. 452. and 454 as shown in FIG. 4(c).
- the definite article is deleted from record set 430 as shown in record set 450.
- the word from of transformed record set 454 is shown in its Chinese form, that is sh ⁇ .
- record sets 440. 442. and 444 is mapped to record sets 460. 462. and 464. wherein the definite article is deleted in record set 460 and the word form in record set 464 is shown herein for illustrative pu ⁇ oses as the Chinese word form zhu ⁇ i.
- the next mapping rule that occurs in this example is transforming the prepositional phrase at metaverb record set 422 according to dictates of Chinese grammar.
- this mapping rule causes record sets 452 and 462 to be swapped and the Chinese particle de to be added after the preposition shdng (for " on " ).
- new keys values should be assigned to reflect that the former right-hand side (record set -1 ) now follows the former left-hand side (record set +1 ). In one such implementation, an extra column for the new key is added to the split table.
- the next mapping rule whose result is shown in FIG. 4(e), handles transitive verbs.
- the target word stream is reconstructed by the word stream construction module 206 from the transformed split tree.
- the nodes of the split tree that is the record sets, are successively visited in step 370, preferably in a bottom-to-top, left-to-right order.
- each metaverb record set 0 is converted into a record set that also includes the metanoun record sets -1 and +1.
- FIGS. 4(a) — 4(f) illustrate the split tree with a source or target language word form instead of a key into the universal dictionary 236. it is during this step that the universal dictionary 236 key is finally resolved into the target word form by a look up operation.
- record sets 450. 452. and 454 are first visited. In the relational database implementation, these records can be chosen by selecting the records with the highest level number and the highest new key values.
- the combination record sets 450. 452. and 454. which is trivial, is reflect in record set 474 as "sh ⁇ " .
- the other level 3 record sets namely record sets 460. 462. and 464, are reconstructed into record set 470 as "zhu ⁇ zi " .
- record set 484 is the Chinese target text that corresponds to the English source text of " the book under the table. " At a still higher level, record set 480 with " w ⁇ ” . record set 482 with “yuel ⁇ n ... le ' and record set 484 with "zhu ⁇ zi sh ⁇ ng de sh ⁇ " are combined together.
- the reconstructed final order shown in result set 490 is " w ⁇ yuel ⁇ n zhu ⁇ zi sh ⁇ ng de shit lej because the particle le belongs at the end of the clause, as the Chinese translation of the English clause " I have read the book under the table.”
- Special word place rules may be handled by the mapping rules in one embodiment or by special reconstruction rules in an alternative embodiment.
- the target word stream undergoes a post-processing step 390 by post-processor 220.
- Post-processor 220 performs analogous sensory medium conversions, similar but opposite of the conversions performed by pre-processor 210.
- the result of post-processing in step 390 may be a digital signal representing text in the target language, an acoustic signal representing speech in the target language (as by a speech synthesizer), and an optical signal representing characters in the target language, for example, as displayed on a cathode-ray tube or printed out on a piece of paper.
- the universal language translation model described herein is a very powerful mechanism for manipulating information in any form. Therefore, the present invention is not limited merely to translating from one human language to another. In fact, the principles discussed herein are applicable to transforming any source signal that embodies information. Information may be defined as a knowledge representation relating to any knowledge discipline that is ultimately useful to any sentient or conscious creature such as human being.
- HTML HyperText Markup Language
- ssytems such as such as A/D converters and satellite systems
- biological orders such as DNA replication.
- embodiments are applicable to controlling dynamic systems such as factories, power plants, and financial institutions.
- artificial languages such as computer source programming languages are fairly straightforward to translate, because programming languages are much less ambiguous than natural languages.
- computer source can be translated into object code like a conventional compiler, into the source code of another high-level language such a FORTRAN to C++.
- object code that is machine-executable instructions, embody information in the operations the computer will carry out.
- object code can be transformed into knowledge embodiments according to other knowledge representations, for example, source code, object code for another processor, and even a natural, human language.
- object code can be translated into the hardware description language, and then directly manufactured. Since some implementations are capable of translating natural and artificial languages into a object code and since object code can be translated into hardware, a mechanism is provided for building Application Specific Integrated Circuits (ASICs) from a functional source code program, an executable file, even a precise English language description, for example. " Make me an operational amplifier having a gain of " .
- ASICs Application Specific Integrated Circuits
- a universal machine translator can be integrated into telecommunications devices to produce a "univers communicator.
- the pre-processing unit 210 and post-processing unit 220 can be coupled into a wireless or wireline telephone system and network, a multimedia communications system, a modem, a facsimile machine or telecopier, a computer system and/or network, a pager, a radio and/or television system, a radar, sonar, infrared, and optical communications system, a photocopy machine, a hand-held, lap-top. or body-worn communications device, or another other machine communications device for machine and operation in any knowledge discipline.
Abstract
Description
Claims
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP99960475A EP1131743B1 (en) | 1998-11-19 | 1999-11-19 | Universal translation method |
AT99960475T ATE287108T1 (en) | 1998-11-19 | 1999-11-19 | UNIVERSAL TRANSLATION PROCESS |
AU17354/00A AU1735400A (en) | 1998-11-19 | 1999-11-19 | Universal translation method |
CA002351406A CA2351406A1 (en) | 1998-11-19 | 1999-11-19 | Universal translation method |
DE69923216T DE69923216D1 (en) | 1998-11-19 | 1999-11-19 | UNIVERSAL TRANSLATION PROCEDURE |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/195,040 | 1998-11-19 | ||
US09/195,040 US6233546B1 (en) | 1998-11-19 | 1998-11-19 | Method and system for machine translation using epistemic moments and stored dictionary entries |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2000029978A1 true WO2000029978A1 (en) | 2000-05-25 |
Family
ID=22719843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US1999/027364 WO2000029978A1 (en) | 1998-11-19 | 1999-11-19 | Universal translation method |
Country Status (7)
Country | Link |
---|---|
US (1) | US6233546B1 (en) |
EP (1) | EP1131743B1 (en) |
AT (1) | ATE287108T1 (en) |
AU (1) | AU1735400A (en) |
CA (1) | CA2351406A1 (en) |
DE (1) | DE69923216D1 (en) |
WO (1) | WO2000029978A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SG98497A1 (en) * | 2001-10-31 | 2003-09-19 | Asgent Inc | Electronic equipment setting information creating method and apparatus, and security policy creating method and associated apparatus |
WO2007141229A1 (en) * | 2006-06-09 | 2007-12-13 | Engineering & Security S.R.L. | Voice translation method and portable interactive device for implementing this method |
US9330331B2 (en) | 2013-11-11 | 2016-05-03 | Wipro Limited | Systems and methods for offline character recognition |
Families Citing this family (84)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6424969B1 (en) * | 1999-07-20 | 2002-07-23 | Inmentia, Inc. | System and method for organizing data |
AU1415201A (en) * | 1999-11-17 | 2001-06-04 | Hiroshi Uchida | Language translation system |
CN1415097A (en) * | 1999-11-17 | 2003-04-30 | 联合国 | System for creating expression in universal language, and recorded medium on which translation rules used for the system are recorded |
US6556973B1 (en) * | 2000-04-19 | 2003-04-29 | Voxi Ab | Conversion between data representation formats |
US9788058B2 (en) | 2000-04-24 | 2017-10-10 | Comcast Cable Communications Management, Llc | Method and system for automatic insertion of interactive TV triggers into a broadcast data stream |
US7702995B2 (en) * | 2000-04-24 | 2010-04-20 | TVWorks, LLC. | Method and system for transforming content for execution on multiple platforms |
US8936101B2 (en) | 2008-07-17 | 2015-01-20 | Halliburton Energy Services, Inc. | Interventionless set packer and setting method for same |
US8296792B2 (en) * | 2000-04-24 | 2012-10-23 | Tvworks, Llc | Method and system to provide interactivity using an interactive channel bug |
US20020010928A1 (en) * | 2000-04-24 | 2002-01-24 | Ranjit Sahota | Method and system for integrating internet advertising with television commercials |
US7437669B1 (en) * | 2000-05-23 | 2008-10-14 | International Business Machines Corporation | Method and system for dynamic creation of mixed language hypertext markup language content through machine translation |
KR20020045343A (en) * | 2000-12-08 | 2002-06-19 | 오길록 | Method of information generation and retrieval system based on a standardized Representation format of sentences structures and meanings |
US7346491B2 (en) * | 2001-01-04 | 2008-03-18 | Agency For Science, Technology And Research | Method of text similarity measurement |
US6944619B2 (en) * | 2001-04-12 | 2005-09-13 | Primentia, Inc. | System and method for organizing data |
CN1266645C (en) * | 2001-05-28 | 2006-07-26 | 河野善弥 | Automatic knowledge creating method, knowledge automatic creating system, knowledge automatic creating program, automatic designing method and automatic design system |
FR2825496B1 (en) * | 2001-06-01 | 2003-08-15 | Synomia | METHOD AND SYSTEM FOR BROAD SYNTAXIC ANALYSIS OF CORPUSES, ESPECIALLY SPECIALIZED CORPUSES |
GB2376554B (en) * | 2001-06-12 | 2005-01-05 | Hewlett Packard Co | Artificial language generation and evaluation |
WO2003005166A2 (en) | 2001-07-03 | 2003-01-16 | University Of Southern California | A syntax-based statistical translation model |
US6701333B2 (en) * | 2001-07-17 | 2004-03-02 | Hewlett-Packard Development Company, L.P. | Method of efficient migration from one categorization hierarchy to another hierarchy |
WO2004001623A2 (en) | 2002-03-26 | 2003-12-31 | University Of Southern California | Constructing a translation lexicon from comparable, non-parallel corpora |
US20030203370A1 (en) * | 2002-04-30 | 2003-10-30 | Zohar Yakhini | Method and system for partitioning sets of sequence groups with respect to a set of subsequence groups, useful for designing polymorphism-based typing assays |
US7054804B2 (en) * | 2002-05-20 | 2006-05-30 | International Buisness Machines Corporation | Method and apparatus for performing real-time subtitles translation |
US20040098250A1 (en) * | 2002-11-19 | 2004-05-20 | Gur Kimchi | Semantic search system and method |
US20040158561A1 (en) * | 2003-02-04 | 2004-08-12 | Gruenwald Bjorn J. | System and method for translating languages using an intermediate content space |
US7181396B2 (en) * | 2003-03-24 | 2007-02-20 | Sony Corporation | System and method for speech recognition utilizing a merged dictionary |
US7711545B2 (en) * | 2003-07-02 | 2010-05-04 | Language Weaver, Inc. | Empirical methods for splitting compound words with application to machine translation |
US8548794B2 (en) | 2003-07-02 | 2013-10-01 | University Of Southern California | Statistical noun phrase translation |
JP3962382B2 (en) * | 2004-02-20 | 2007-08-22 | インターナショナル・ビジネス・マシーンズ・コーポレーション | Expression extraction device, expression extraction method, program, and recording medium |
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 |
US7580837B2 (en) | 2004-08-12 | 2009-08-25 | At&T Intellectual Property I, L.P. | System and method for targeted tuning module of a speech recognition system |
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 |
US7242751B2 (en) * | 2004-12-06 | 2007-07-10 | Sbc Knowledge Ventures, L.P. | System and method for speech recognition-enabled automatic call routing |
US7751551B2 (en) | 2005-01-10 | 2010-07-06 | At&T Intellectual Property I, L.P. | System and method for speech-enabled call routing |
JP2006268375A (en) * | 2005-03-23 | 2006-10-05 | Fuji Xerox Co Ltd | Translation memory system |
JP2006276918A (en) * | 2005-03-25 | 2006-10-12 | Fuji Xerox Co Ltd | Translating device, translating method and program |
US7548849B2 (en) * | 2005-04-29 | 2009-06-16 | Research In Motion Limited | Method for generating text that meets specified characteristics in a handheld electronic device and a handheld electronic device incorporating the same |
US7657020B2 (en) | 2005-06-03 | 2010-02-02 | At&T Intellectual Property I, Lp | Call routing system and method of using the same |
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 |
US10319252B2 (en) | 2005-11-09 | 2019-06-11 | Sdl Inc. | Language capability assessment and training apparatus and techniques |
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 |
US8886518B1 (en) | 2006-08-07 | 2014-11-11 | Language Weaver, Inc. | System and method for capitalizing machine translated text |
US9495358B2 (en) | 2006-10-10 | 2016-11-15 | Abbyy Infopoisk Llc | Cross-language text clustering |
US9471562B2 (en) | 2006-10-10 | 2016-10-18 | Abbyy Infopoisk Llc | Method and system for analyzing and translating various languages with use of semantic hierarchy |
US9053090B2 (en) * | 2006-10-10 | 2015-06-09 | Abbyy Infopoisk Llc | Translating texts between languages |
US8145473B2 (en) | 2006-10-10 | 2012-03-27 | Abbyy Software Ltd. | Deep model statistics method for machine translation |
US9633005B2 (en) | 2006-10-10 | 2017-04-25 | Abbyy Infopoisk Llc | Exhaustive automatic processing of textual information |
US8195447B2 (en) | 2006-10-10 | 2012-06-05 | Abbyy Software Ltd. | Translating sentences between languages using language-independent semantic structures and ratings of syntactic constructions |
US9235573B2 (en) | 2006-10-10 | 2016-01-12 | Abbyy Infopoisk Llc | Universal difference measure |
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 |
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 |
CN101303692B (en) * | 2008-06-19 | 2012-08-29 | 徐文和 | All-purpose numeral semantic library for translation of mechanical language |
JP2010055235A (en) * | 2008-08-27 | 2010-03-11 | Fujitsu Ltd | Translation support program and system thereof |
US20100082324A1 (en) * | 2008-09-30 | 2010-04-01 | Microsoft Corporation | Replacing terms in machine translation |
KR101045762B1 (en) * | 2008-11-03 | 2011-07-01 | 한국과학기술원 | Real-time semantic annotation device and method for generating natural language string input by user as semantic readable knowledge structure document in real time |
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 |
KR101301536B1 (en) * | 2009-12-11 | 2013-09-04 | 한국전자통신연구원 | Method and system for serving foreign language translation |
US10417646B2 (en) | 2010-03-09 | 2019-09-17 | Sdl Inc. | Predicting the cost associated with translating textual content |
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 |
US8935719B2 (en) | 2011-08-25 | 2015-01-13 | Comcast Cable Communications, Llc | Application triggering |
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 |
US9152622B2 (en) | 2012-11-26 | 2015-10-06 | Language Weaver, Inc. | Personalized machine translation via online adaptation |
US9414114B2 (en) | 2013-03-13 | 2016-08-09 | Comcast Cable Holdings, Llc | Selective interactivity |
US9460088B1 (en) * | 2013-05-31 | 2016-10-04 | Google Inc. | Written-domain language modeling with decomposition |
US10025778B2 (en) * | 2013-06-09 | 2018-07-17 | Microsoft Technology Licensing, Llc | Training markov random field-based translation models using gradient ascent |
US9213694B2 (en) | 2013-10-10 | 2015-12-15 | Language Weaver, Inc. | Efficient online domain adaptation |
RU2592395C2 (en) | 2013-12-19 | 2016-07-20 | Общество с ограниченной ответственностью "Аби ИнфоПоиск" | Resolution semantic ambiguity by statistical analysis |
RU2586577C2 (en) | 2014-01-15 | 2016-06-10 | Общество с ограниченной ответственностью "Аби ИнфоПоиск" | Filtering arcs parser graph |
US11076205B2 (en) | 2014-03-07 | 2021-07-27 | Comcast Cable Communications, Llc | Retrieving supplemental content |
RU2596600C2 (en) | 2014-09-02 | 2016-09-10 | Общество с ограниченной ответственностью "Аби Девелопмент" | Methods and systems for processing images of mathematical expressions |
US9626358B2 (en) | 2014-11-26 | 2017-04-18 | Abbyy Infopoisk Llc | Creating ontologies by analyzing natural language texts |
CN106383818A (en) | 2015-07-30 | 2017-02-08 | 阿里巴巴集团控股有限公司 | Machine translation method and device |
US10346547B2 (en) * | 2016-12-05 | 2019-07-09 | Integral Search International Limited | Device for automatic computer translation of patent claims |
US10318633B2 (en) * | 2017-01-02 | 2019-06-11 | International Business Machines Corporation | Using multilingual lexical resources to improve lexical simplification |
US10318634B2 (en) * | 2017-01-02 | 2019-06-11 | International Business Machines Corporation | Enhancing QA system cognition with improved lexical simplification using multilingual resources |
US20230120230A1 (en) * | 2021-10-20 | 2023-04-20 | Transfluent Oy | Method and system for translating source text of first language to second language |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1998049629A1 (en) * | 1997-05-01 | 1998-11-05 | Datig William E | Universal epistemological machine (a.k.a. android) |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4286330A (en) | 1976-04-07 | 1981-08-25 | Isaacson Joel D | Autonomic string-manipulation system |
JPH04111121A (en) * | 1990-08-31 | 1992-04-13 | Fujitsu Ltd | Dictionary producer by field classification and mechanical translator and mechanical translation system using the same |
US5481700A (en) | 1991-09-27 | 1996-01-02 | The Mitre Corporation | Apparatus for design of a multilevel secure database management system based on a multilevel logic programming system |
US5632022A (en) | 1991-11-13 | 1997-05-20 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Encyclopedia of software components |
US5495413A (en) * | 1992-09-25 | 1996-02-27 | Sharp Kabushiki Kaisha | Translation machine having a function of deriving two or more syntaxes from one original sentence and giving precedence to a selected one of the syntaxes |
JP2821840B2 (en) * | 1993-04-28 | 1998-11-05 | 日本アイ・ビー・エム株式会社 | Machine translation equipment |
US5659765A (en) * | 1994-03-15 | 1997-08-19 | Toppan Printing Co., Ltd. | Machine translation system |
JP3356536B2 (en) * | 1994-04-13 | 2002-12-16 | 松下電器産業株式会社 | Machine translation equipment |
JPH09128396A (en) * | 1995-11-06 | 1997-05-16 | Hitachi Ltd | Preparation method for bilingual dictionary |
-
1998
- 1998-11-19 US US09/195,040 patent/US6233546B1/en not_active Expired - Fee Related
-
1999
- 1999-11-19 EP EP99960475A patent/EP1131743B1/en not_active Expired - Lifetime
- 1999-11-19 CA CA002351406A patent/CA2351406A1/en not_active Abandoned
- 1999-11-19 AU AU17354/00A patent/AU1735400A/en not_active Abandoned
- 1999-11-19 AT AT99960475T patent/ATE287108T1/en not_active IP Right Cessation
- 1999-11-19 DE DE69923216T patent/DE69923216D1/en not_active Expired - Lifetime
- 1999-11-19 WO PCT/US1999/027364 patent/WO2000029978A1/en active IP Right Grant
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1998049629A1 (en) * | 1997-05-01 | 1998-11-05 | Datig William E | Universal epistemological machine (a.k.a. android) |
Non-Patent Citations (4)
Title |
---|
ARNOLD: "Eurotra: A European Perspective on MT", PROCEEDINGS OF THE IEEE, vol. 74, no. 7, July 1986 (1986-07-01), New York, NY, US, pages 979 - 992, XP000756005 * |
HOVY: "HOW MT WORKS", BYTE, vol. 18, no. 1, January 1993 (1993-01-01), London, GB, pages 167 - 176, XP000334434 * |
SIMMONS: "Technologies for Machine Translation", FUTURE GENERATIONS COMPUTER SYSTEMS, vol. 2, no. 2, June 1986 (1986-06-01), Amsterdam, NL, pages 83 - 94, XP000648180 * |
SLOCUM: "Machine Translation: An American Perspective", PROCEEDINGS OF THE IEEE, vol. 74, no. 7, July 1986 (1986-07-01), New York, NY, US, pages 969 - 978, XP000756007 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SG98497A1 (en) * | 2001-10-31 | 2003-09-19 | Asgent Inc | Electronic equipment setting information creating method and apparatus, and security policy creating method and associated apparatus |
US7337105B2 (en) | 2001-10-31 | 2008-02-26 | Asgent, Inc. | Electronic equipment setting information creating method and apparatus, and security policy creating method and associated apparatus |
WO2007141229A1 (en) * | 2006-06-09 | 2007-12-13 | Engineering & Security S.R.L. | Voice translation method and portable interactive device for implementing this method |
US9330331B2 (en) | 2013-11-11 | 2016-05-03 | Wipro Limited | Systems and methods for offline character recognition |
Also Published As
Publication number | Publication date |
---|---|
DE69923216D1 (en) | 2005-02-17 |
EP1131743B1 (en) | 2005-01-12 |
ATE287108T1 (en) | 2005-01-15 |
AU1735400A (en) | 2000-06-05 |
EP1131743A1 (en) | 2001-09-12 |
US6233546B1 (en) | 2001-05-15 |
CA2351406A1 (en) | 2000-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1131743B1 (en) | Universal translation method | |
Brill et al. | An overview of empirical natural language processing | |
Sumita et al. | Translating with examples: a new approach to machine translation | |
US9798720B2 (en) | Hybrid machine translation | |
Sornlertlamvanich et al. | Building a Thai part-of-speech tagged corpus (ORCHID) | |
US6760695B1 (en) | Automated natural language processing | |
JP2000353161A (en) | Method and device for controlling style in generation of natural language | |
Grif et al. | Development of computer sign language translation technology for deaf people | |
Boguslavsky et al. | Creating a Universal Networking Language module within an advanced NLP system | |
WO1997040453A1 (en) | Automated natural language processing | |
Anwar et al. | Syntax analysis and machine translation of Bangla sentences | |
Schubert | The architecture of DLT| Interlingual or double direct | |
Mousa | Natural language processing (nlp) | |
Hutchins | Research methods and system designs in machine translation: a ten-year review, 1984-1994 | |
Sethi et al. | Hybridization based machine translations for low-resource language with language divergence | |
Papageorgiou et al. | Multi-level XML-based Corpus Annotation. | |
Agarwal et al. | UNLization of Punjabi text for natural language processing applications | |
Vasconcellos et al. | Terminology and machine translation | |
Mohamed | Machine Translation of Noun Phrases from English to Arabic | |
Boitet | GETA's MT methodology and its current development towards personal networking communication and speech translation in the context of the UNL and C-STAR projects | |
Hanane et al. | A model of a generic Arabic language interface for multimodel database | |
Agiza et al. | An English-to-Arabic Prototype Machine Translator for Statistical Sentences | |
Bharati et al. | Paninian framework and its application to Anusaraka | |
Samantaray | A Data mining approach for resolving cases of Multiple Parsing in Machine Aided Translation of Indian Languages | |
Lehmann et al. | Human language and computers |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref country code: AU Ref document number: 2000 17354 Kind code of ref document: A Format of ref document f/p: F |
|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AL AM AT AU AZ BA BB BG BR BY CA CH CN CR CZ DE DK DM EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KR KZ LC LK LR LS LT LU LV MD MG MK MN MW MX NO NZ PL PT RO RU SD SE SG SI SK SL TJ TM TR TT TZ UA UG UZ VN YU ZA ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GH GM KE LS MW SD SL SZ TZ UG ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE BF BJ CF CG CI CM GA GN GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
ENP | Entry into the national phase |
Ref document number: 2351406 Country of ref document: CA Ref country code: CA Ref document number: 2351406 Kind code of ref document: A Format of ref document f/p: F |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1999960475 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 1999960475 Country of ref document: EP |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
WWG | Wipo information: grant in national office |
Ref document number: 1999960475 Country of ref document: EP |