EP0525470A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method and system for natural language translation
Assignee: International Business Machines Corp
•
Filing: 1992-07-10
•
Granted: —
•
Expires: 2012-07-10
Abstract
Abstract The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.
Inventors
- 👤 Peter Fitzhugh Brown
- 👤 John Cocke
- 👤 Stephen Andrew Della Pietra
- 👤 Vincent Joseph Della Pietra
- 👤 Frederick Jelinek
- 👤 Jennifer Ceil Lai
- 👤 Robert Leroy Mercer
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-01 08:03
CPC Classifications
G; G06; G06F; G06F40/00; G06F40/40; G06F40/42; G06F40/44; G06F40/20; G06F40/268; G06F40/49; G06F40/55
Claims Analysis
Total Claims: 48
Claim 1
Independent Claim
161 words
A method operating on a computer for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: measuring the value of the source text in the first language and storing the source text in a first memory buffer; generating the target text in the second language based on a combination of the probability of occurrence of an intermediate structure of text associated with a target hypothesis selected from the second language using a target language model, and the probability of occurrence of the source text given the occurrence of said intermediate structure of text associated with said target hypothesis using a target-to-source translation model; and performing at least one of a storing and presenting operation to save said target text in a second memory buffer or otherwise make said target text available for at least one of a viewing and listening operation using an I/O device.
Claim 2
Independent Claim
161 words
A method operating on a computer for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: measuring the value of the source text in the first language and storing the source text in a first memory buffer; generating the target text in the second language based on a combination of the probability of occurrence of an intermediate structure of text associated with a target hypothesis selected from the second language using a target language model, and the probability of occurrence of the source text given the occurrence of said intermediate structure of text associated with said target hypothesis using a target-to-source translation model; and performing at least one of a storing and presenting operation to save said target text in a second memory buffer or otherwise make said target text available for at least one of a viewing and listening operation using an I/O device.
Claim 3
Independent Claim
164 words
A method for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: receiving the source text in the first language; generating at least one target hypothesis, each of said target hypothesis comprising text selected from the second language; estimating, for each target hypothesis, a first probability of occurrence of said text associated with said target hypothesis using a target language model; estimating, for each target hypothesis, a second probability of occurrence of the source text given the occurrence of said text associated with said target hypothesis using a target-to-source translation model; combining, for each target hypothesis, said first and second probabilities to produce a target hypothesis match score; and performing at least one of a storing and presenting operation to save or otherwise make available for at least one of a viewing and listening operation, at least one of said target hypotheses according to its associated match score.
Claim 4
Independent Claim
164 words
A method for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: receiving the source text in the first language; generating at least one target hypothesis, each of said target hypothesis comprising text selected from the second language; estimating, for each target hypothesis, a first probability of occurrence of said text associated with said target hypothesis using a target language model; estimating, for each target hypothesis, a second probability of occurrence of the source text given the occurrence of said text associated with said target hypothesis using a target-to-source translation model; combining, for each target hypothesis, said first and second probabilities to produce a target hypothesis match score; and performing at least one of a storing and presenting operation to save or otherwise make available for at least one of a viewing and listening operation, at least one of said target hypotheses according to its associated match score.
Claim 5
Dependent Claim
174 words
A computer system for translating source text from a first language to target text in a second language different from the first language, said system comprising: means for receiving the source text in the first language; means for generating at least one target hypothesis, each of said target hypotheses comprising text selected from the second language; means for estimating, for each target hypothesis, a first probability of occurrence of said text associated with said target hypothesis using a target language model; means for estimating, for each target hypothesis, a second probability of occurrence of the source text given the occurrence of said text associated with said target hypothesis using a target-to-source translation model; means for combining, for each target hypothesis, said first and second probabilities to produce a target hypothesis match score; and means for performing at least one of a storing and presenting operation to save or otherwise make available for at least one of a viewing and listening operation, at least one of said target hypotheses according to its associated match score.
Claim 6
Dependent Claim
174 words
A computer system for translating source text from a first language to target text in a second language different from the first language, said system comprising: means for receiving the source text in the first language; means for generating at least one target hypothesis, each of said target hypotheses comprising text selected from the second language; means for estimating, for each target hypothesis, a first probability of occurrence of said text associated with said target hypothesis using a target language model; means for estimating, for each target hypothesis, a second probability of occurrence of the source text given the occurrence of said text associated with said target hypothesis using a target-to-source translation model; means for combining, for each target hypothesis, said first and second probabilities to produce a target hypothesis match score; and means for performing at least one of a storing and presenting operation to save or otherwise make available for at least one of a viewing and listening operation, at least one of said target hypotheses according to its associated match score.
Claim 7
Dependent Claim
85 words
A method according to claim 2 or 3, further comprising the steps of: generating a list of partial target hypotheses using said target language model and said target-to-source translation model; extending said partial hypotheses to generate a set of new hypotheses; determining a match score for at least one of said new hypotheses; and performing at least one of a storing and presenting operation to save or otherwise make available for viewing, at least one of said new hypotheses according to its associated match score.
Claim 8
Independent Claim
80 words
A method according to one of clams 1 to 4, further comprising the step of: receiving at least one user defined criteria pertaining to the source text to thereby bound the target text, said criteria belonging to the group comprising specification of a noun phrase, specification of subject, specification of verb, a semantic sense of a word or group of words, inclusion of a predetermined word or group of words, and exclusion of a predetermined word or group of words.
Claim 9
Independent Claim
80 words
A method according to one of clams 1 to 4, further comprising the step of: receiving at least one user defined criteria pertaining to the source text to thereby bound the target text, said criteria belonging to the group comprising specification of a noun phrase, specification of subject, specification of verb, a semantic sense of a word or group of words, inclusion of a predetermined word or group of words, and exclusion of a predetermined word or group of words.
Claim 10
Dependent Claim
69 words
A method according to claim 4 or 5, wherein said match score determining step further comprises the steps of: determining a language model score for each of said partial hypotheses using said target language model; determining a translation model score for each of said partial hypotheses using said target-to-source translation model; and determining a combined score of said language and translation model scores for each of said partial hypotheses.
Claim 11
Dependent Claim
241 words
A method according to claim 6, wherein said translation model score determining step further comprises at least one of the following steps: determining a fertility model score for each of said partial hypotheses, said partial hypotheses comprising at least one notion and said fertility model score being proportional to the probability that a notion in the target text will generate a specific number of notion units of linguistic structure in the source text; determining an alignment score for each of said partial hypotheses, said alignment score being proportional to the probability that a unit of linguistic structure in the target text will align with one of zero or more units of linguistic structure in the source text; determining a lexical model score, for each of said partial hypotheses, said lexical model score being proportional to the probability that said units of linguistic structure in the target text of a given partial hypothesis will translate into said units of linguistic structure of said source text; determining a distortion model score for each of said partial hypotheses, said distortion model score being proportional to the probability that a source of linguistic structure will be in a particular position given the position of the target units of linguistic structure that generated it; and determining a combined score, said combined score being proportional to the product of at least one of said fertility, alignment, lexical and distortion model scores for each of said partial hypotheses.
Claim 12
Dependent Claim
260 words
A method according to claim 6, wherein said translation model score determining step further comprises at least one of the following steps: determining a fertility model score for each of said partial hypotheses, said partial hypotheses comprising at least one notion and said fertility model score being proportional to the probability that a notion in an intermediate structure of the target text will generate a specific number of notion units of linguistic structure in an intermediate structure source text; determining an alignment score for each of said partial hypotheses, said alignment score being proportional to the probability that a unit of linguistic structure in said intermediate structure of target text will align with one of zero or more units of linguistic structure in said intermediate structure of source text; determining a lexical model score, for each of said partial hypothesis, said lexical model score being proportional to the probability that said units of linguistic structure in said intermediate structure of target text of a given partial hypothesis will translate into said units of linguistic structure of said intermediate structure of source text; determining a distortion model score for each of said partial hypotheses, said distortion model score being proportional to the probability that a source unit of linguistic structure will be in a particular position given the position of the target units of linguistic structure that generated it; and determining a combined score, said combined score being proportional to the product of at least one of said fertility, alignment, lexical and distortion model scores for each of said partial hypotheses.
Claim 13
Dependent Claim
47 words
A method according to claim 7 or 8, wherein each of said notions comprises at least one unit of linguistic structure, and each of said units of linguistic structure in the target text produces one of zero or more units of linguistic structure in the source text.
Claim 14
Independent Claim
302 words
A method operating on a computer for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: receiving the source text in the first language and storing the source text in a first memory buffer; receiving one of zero or more user defined criteria pertaining to the source and target texts to thereby bound the target text; accessing the source text from said first buffer and transducing the source text into at least one intermediate source structure of text constrained by any of said user defined criteria; generating at least one target hypothesis, each of said target hypotheses comprising an intermediate target structure of text selected from the second language constrained by any of said user defined criteria; estimating a first score, said first score being proportional to the probability of occurrence of each intermediate target structure of text associated with said target hypotheses using a target structure language model; estimating a second score, said second score being proportional to the probability that said intermediate target structure of text associated with said target hypotheses will translate into said intermediate source structure of text using a target structure-to-source structure translation model; combining, for each target hypothesis, said first and second scores to produce a target hypothesis match score; transducing each of said intermediate target structures of text into at least one transformed target hypothesis of text in the second language constrained by any of said user defined criteria; and performing at least one of a storing and presenting operation to save said at least one transformed target hypothesis in a second memory buffer or otherwise make available for at least one of a viewing and listening operation according to its associated match score and said user defined criteria.
Claim 15
Independent Claim
302 words
A method operating on a computer for translating source text from a first language to target text in a second language different from the first language, said method comprising the steps of: receiving the source text in the first language and storing the source text in a first memory buffer; receiving one of zero or more user defined criteria pertaining to the source and target texts to thereby bound the target text; accessing the source text from said first buffer and transducing the source text into at least one intermediate source structure of text constrained by any of said user defined criteria; generating at least one target hypothesis, each of said target hypotheses comprising an intermediate target structure of text selected from the second language constrained by any of said user defined criteria; estimating a first score, said first score being proportional to the probability of occurrence of each intermediate target structure of text associated with said target hypotheses using a target structure language model; estimating a second score, said second score being proportional to the probability that said intermediate target structure of text associated with said target hypotheses will translate into said intermediate source structure of text using a target structure-to-source structure translation model; combining, for each target hypothesis, said first and second scores to produce a target hypothesis match score; transducing each of said intermediate target structures of text into at least one transformed target hypothesis of text in the second language constrained by any of said user defined criteria; and performing at least one of a storing and presenting operation to save said at least one transformed target hypothesis in a second memory buffer or otherwise make available for at least one of a viewing and listening operation according to its associated match score and said user defined criteria.
Claim 16
Dependent Claim
321 words
A computer system for translating source text from a first language to target text in a second language different from the first language, said system comprising: means for receiving the source text in the first language and storing the source text in a first memory buffer; means for receiving one of zero or more user defined criteria pertaining to the source and target texts to thereby bound the target text; means for accessing the source text from said first buffer; first transducing means for transducing the source text into at least one intermediate source structure of text constrained by any of said user defined criteria; means for generating at least one target hypothesis, each of said target hypotheses comprising a intermediate target structure of text selected from the second language constrained by any of said user defined criteria; means for estimating a first score, said first score being proportional to the probability of occurrence of each intermediate target structure of text associated with said target hypotheses using a target structure language model; means for estimating a second score, said second score being proportional to the probability that said intermediate target structure of text associated with said target hypothesis will translate into said intermediate source structure of text using a target structure-to-source structure translation model; means for combining, for each target hypothesis, said first and second scores to produce a target hypothesis match score; second transducing means for transducing each of said intermediate target structures of text into at least one transformed target hypothesis of text in the second language constrained by any of said user defined criteria; and means for at least one of storing said at least one transformed target hypothesis in a second memory buffer, and presenting or otherwise making said at least one transformed target hypothesis available for at least one of a viewing and listening operation according to its associated match score and said user defined criteria.
Claim 17
Dependent Claim
321 words
A computer system for translating source text from a first language to target text in a second language different from the first language, said system comprising: means for receiving the source text in the first language and storing the source text in a first memory buffer; means for receiving one of zero or more user defined criteria pertaining to the source and target texts to thereby bound the target text; means for accessing the source text from said first buffer; first transducing means for transducing the source text into at least one intermediate source structure of text constrained by any of said user defined criteria; means for generating at least one target hypothesis, each of said target hypotheses comprising a intermediate target structure of text selected from the second language constrained by any of said user defined criteria; means for estimating a first score, said first score being proportional to the probability of occurrence of each intermediate target structure of text associated with said target hypotheses using a target structure language model; means for estimating a second score, said second score being proportional to the probability that said intermediate target structure of text associated with said target hypothesis will translate into said intermediate source structure of text using a target structure-to-source structure translation model; means for combining, for each target hypothesis, said first and second scores to produce a target hypothesis match score; second transducing means for transducing each of said intermediate target structures of text into at least one transformed target hypothesis of text in the second language constrained by any of said user defined criteria; and means for at least one of storing said at least one transformed target hypothesis in a second memory buffer, and presenting or otherwise making said at least one transformed target hypothesis available for at least one of a viewing and listening operation according to its associated match score and said user defined criteria.
Claim 18
Dependent Claim
46 words
A method according to claim 10 or 11, wherein said intermediate source and target structures are transduced by: arranging and rearranging, respectively, elements of the source and target text according to at least one of lexical substitutions, part-of-speech assignment, a morphological analysis, and a syntactic analysis.
Claim 19
Independent Claim
44 words
A method according to one of claims 10 to 12, wherein said intermediate source structure transducing step further comprises the step of: tokenizing the source text by identifying individual words and word separators and arranging said words and said word separators in a sequence.
Claim 20
Independent Claim
65 words
A method according to one of claims 10 to 13, wherein each of said intermediate target structures is expressed as an ordered sequence of units of linguistic structure, and said first score probability is obtained by multiplying the conditional probabilities of each units of linguistic structure within an intermediate target structure given the occurence of previous units of linguistic structure within said intermediate target structure.
Claim 21
Dependent Claim
34 words
A method according to claim 14, wherein said conditional probability of each unit of each of said intermediate target structures depends only on a fixed number of preceding units within said intermediate target structure.
Claim 22
Independent Claim
70 words
A method according to one of claims 13 to 15, wherein said intermediate source structure transducing step further comprises the step of: determining the case of said words using a case transducer, said case transducer assigning each word a token and a case pattern, said case pattern specifying the case of each letter of the word, and evaluating each case pattern to determine the true case pattern of the word.
Claim 23
Dependent Claim
128 words
A method according to claim 16, wherein said determining step further comprises the steps of: (1) determining whether said token is part of a name; (2) if said token is not part of a name: determining whether said token is a member of a set of tokens which have only one true case; if said token is part of a name: setting the true case according to a table of true cases for names; (3) if the true case has not been determined by steps 1 and 2, and if the token is a first token in a sentence, then: setting the true case equal to the most probable true case for that token; and (4) otherwise: setting the true case equal to the case for that token.
Claim 24
Independent Claim
44 words
A method according to one of claims 12 to 17, wherein said intermediate source structure transducing step further comprises the step of: annotating said words with parts of speech by probablistically assigning a parts of speech to said words according to a statistical model.
Claim 25
Dependent Claim
43 words
A method according to claim 18, wherein said intermediate source structure transducing step further comprises the step of: analyzing, syntactically, said annotated words and outputting a sequence of words and a sequence of said parts of speech corresponding to said sequence of words.
Claim 26
Dependent Claim
40 words
A method according to claim 19, wherein said intermediate source structure transducing step further comprises the step of: analyzing, morphologically, said syntactically analyzed words by performing a morphological analysis of said words in accordance with said assigned parts of speech.
Claim 27
Dependent Claim
41 words
A method according to claim 20, wherein said intermediate source structure transducing step further comprises the step of: assigning a sense to at least one of said morphological units to elucidate the translation of that morphological unit in the target language.
Claim 28
Independent Claim
29 words
A method according to one of claims 12 to 21, wherein said syntactic analysis further comprises the steps of: performing question inversion; performing do-not coalescence; and performing adverb movement.
Claim 29
Independent Claim
36 words
A method according to one of claims 12 to 22, wherein said syntactic analysis further comprises the steps of: performing question inversion; performing negative coalescence; and performing at least one of adverb, pronoun and adjective movement.
Claim 30
Independent Claim
85 words
A method for generating a lexical model for use in a language translation system, comprising the steps of: storing a source training text; storing a target training text; and choosing a specification of parameters for the lexical model so that the likelihood of translating to the source text given the target text is the unique local maximum value, said unique local maximum value being greater than the likelihood of translating to the source text given the target text for any other selection of parameter values.
Claim 31
Independent Claim
85 words
A method for generating a lexical model for use in a language translation system, comprising the steps of: storing a source training text; storing a target training text; and choosing a specification of parameters for the lexical model so that the likelihood of translating to the source text given the target text is the unique local maximum value, said unique local maximum value being greater than the likelihood of translating to the source text given the target text for any other selection of parameter values.
Claim 32
Dependent Claim
91 words
A computer system for generating a lexical model for use in a language translation system, comprising: first means for storing a source training text; second means for storing a target training text; and means for choosing a specification of parameters for the lexical model so that the likelihood of translating the to source text given the target text is the unique local maximum value, said unique local maximum value being greater than the likelihood of translating the to source text given the target text for any other selection of parameter values.
Claim 33
Dependent Claim
91 words
A computer system for generating a lexical model for use in a language translation system, comprising: first means for storing a source training text; second means for storing a target training text; and means for choosing a specification of parameters for the lexical model so that the likelihood of translating the to source text given the target text is the unique local maximum value, said unique local maximum value being greater than the likelihood of translating the to source text given the target text for any other selection of parameter values.
Claim 34
Dependent Claim
63 words
A method according to claim 24 or 25, for training text in two parallel corpora, comprising the steps of: grouping said source training text into a first plurality of tokens having sentence-like structures; grouping said target training text into a second plurality of tokens having sentence-like structures; performing sentence alignment by aligning said first and second pluralities of tokens according to their length.
Claim 35
Dependent Claim
21 words
A method according to claim 26, further comprising the step of determining the probability associated with each of said sentence alignments.
Claim 36
Dependent Claim
30 words
A method according to claim 26 or 27, further comprising the steps of: generating bigram statistics for said tokens; and generating classes of similar elements based on said bigram statistics.
Claim 37
Independent Claim
23 words
A method according to one of claims 24 to 28, wherein said storing steps store a source language and an artificial language, respectively.
Claim 38
Independent Claim
48 words
A method for generating a model for use in a language translation system, comprising the steps of: storing a source training text; storing a target training text; and performing alignment of units of linguistic structure of the source text with units of linguistic structure of the target text.
Claim 39
Independent Claim
48 words
A method for generating a model for use in a language translation system, comprising the steps of: storing a source training text; storing a target training text; and performing alignment of units of linguistic structure of the source text with units of linguistic structure of the target text.
Claim 40
Dependent Claim
52 words
A computer system for generating a model for use in a language translation system, comprising: means for storing a source training text; means for storing a target training text; and means for performing alignment of units of linguistic structure of the source text with units of linguistic structure of the target text.
Claim 41
Dependent Claim
52 words
A computer system for generating a model for use in a language translation system, comprising: means for storing a source training text; means for storing a target training text; and means for performing alignment of units of linguistic structure of the source text with units of linguistic structure of the target text.
Claim 42
Dependent Claim
23 words
A method according to claim 30 or 31, further comprising the step of determining the probability associated with each of said unit alignments.
Claim 43
Independent Claim
37 words
A method according to one of claims 30 to 32, further comprising the step of: determining the sum of probabilities for all alignments of units of linguistic structure for a given pair of source and target sentences.
Claim 44
Independent Claim
37 words
A method according to one of claims 30 to 33, further comprising the step of: determining, for a given pair of source and target sentences, the most probable alignment of units of linguistic structure between the sentences.
Claim 45
Independent Claim
46 words
A method according to one of claims 30 to 34, further comprising the step of: determining, for a given pair of source and target sentences and a given partial alignment of units of linguistic structure between the sentences, the most probable completion of said partial alignment.
Claim 46
Independent Claim
43 words
A method according to one of claims 30 to 35, further comprising the step of: determining, for a given pair of source and target sentences and a completely specified alignment of units of linguistic structure between the sentences, the probability of said alignment.
Claim 47
Dependent Claim
36 words
A method according to claim 35 or 36, further comprising the step of: adjusting said most probable completion of said partial alignment by changing said alignment; and determining the most probable completion of said new alignment.
Claim 48
Dependent Claim
62 words
A method according to claim 37,further comprising the step of: changing said alignment by performing at least one of a swapping and single move operation, said swapping comprising the interchanging of target units of linguistic structure assigned to any two source units of linguistic structure, and said single move comprising the changing of a target unit assigned to any one source unit.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.