EP0805403A2 — Translating apparatus and translating method

Claim 1

Independent Claim 153 words

A translating apparatus for translating a first language sentence expressed in a first language into a secondlanguage sentence expressed in a second language, comprising: example memory means (3) storing examples expressed in said first language and corresponding translations of said examples in said second language; dividing means (4) for dividing said first language sentence into syntax units consisting of predetermined units of sentence structure; detecting means (6) for detecting for each of said syntax units of said first language sentence outputted by said dividing means an example similar to that syntax unit from among said examples; translating means (7) for translating said first language sentence in said syntax units on the basis of those of said translations corresponding to those of said examples detected by said detecting means (6); and generating means (15) for generating said second language sentence by compounding results of translation of said syntax units obtained by said translating means.

Claim 2

Dependent Claim 24 words

A translating apparatus according to claim 1, wherein said example memory means (3) stores said examples and said corresponding translations in said syntax units.

Claim 3

Dependent Claim 28 words

A translating apparatus according to claim 1 or 2, wherein said dividing means (4) divides said first language sentence in stages from large syntax units to small syntaxunits.

Claim 4

Dependent Claim 48 words

A translating apparatus according to claim 3, wherein said dividing means (4) comprises clause dividing means for dividing said first language sentence into clause units and phrase dividing means for dividing said clause units of said first language sentence outputted from said clause dividing means into phrase units.

Claim 5

Dependent Claim 37 words

A translating apparatus according to claim 4, wherein said example memory means (3) comprises clause unit example memory means (5) storing examples in clause units and phrase unit example memory means storing phrase examples in phrase units.

Claim 6

Dependent Claim 27 words

A translating apparatus according to claim 5, wherein said phrase unit example memory means (3) stores said examples classified at least into noun phrases and verb phrases.

Claim 7

Dependent Claim 43 words

A translating apparatus according to claim 3, wherein said dividing means (4) divides said first language sentence into large syntax units and when none of said examples matches any of said large syntax units divides said large syntax units into smaller syntax units.

Claim 8

Dependent Claim 21 words

A translating apparatus according to claim 1, wherein said example memory means (3) stores said examples together with grammatical attributes thereof.

Claim 9

Dependent Claim 61 words

A translating apparatus according to claim 8, wherein said dividing means (4) divides said first language sentence into said syntax units and extracts grammatical attributes of said syntax units by carrying out syntax analysis and said detecting means (6) detects those of said examples similar to said clause units taking into account grammatical attributes of said syntax units and said examples.

Claim 10

Dependent Claim 55 words

A translating apparatus according to anyone of the preceding claims, wherein said detecting means (6) detects said example similar to said syntax unit on the basis of a priori probability of said example being used to translate said syntax unit and a transformation probability of said example being transformed into said syntax unit and used.

Claim 11

Dependent Claim 39 words

A translating apparatus according to claim 10, wherein said transformation probability is calculated from a grammatical attribute transformation probability of grammatical attributes of said example being transformed and a word transformation probability of words of said example being transformed.

Claim 12

Dependent Claim 83 words

A translating apparatus according to claim 11, wherein said grammatical attribute transformation probability is calculated from a grammatical attribute copy probability of a grammatical attribute of said example being used unchanged, a grammatical attribute deletion probability of a grammatical attribute of said example being deleted, a grammatical attribute addition probability of a grammatical attribute of said syntax unit being added, and a grammatical attribute replacement probability of a grammatical attribute of said example being replaced with a grammatical attribute of said syntax unit.

Claim 13

Dependent Claim 73 words

A translating apparatus according to claim 11, wherein said word transformation probability is calculated from a word copy probability of a word of said example being used unchanged, a word deletion probability of a word of said example being deleted, a word addition probability of a word of said syntax unit being added, and a word replacement probability of a word of said example being replaced with a word of said syntax unit.

Claim 14

Dependent Claim 77 words

A translating apparatus according to claim 13, further comprising: thesaurus memory means (12) storing a thesaurus wherein words are classified in a tree structure on the basis of their concepts; and word similarity degree calculating means (11) for calculating a word similarity degree expressing a similarity between a word of said syntax unit and a word of said example on the basis of said thesaurus (12) and outputting said word similarity degree as said word replacement probability.

Claim 15

Dependent Claim 49 words

A translating apparatus according to claim 14, wherein said word similarity degree calculating means (11) calculates said word similarity degree on the basis of the number of words included in a concept common to said word of said syntax unit and said word of said example in said thesaurus.

Claim 16

Dependent Claim 28 words

A translating apparatus according to claim 11, wherein said word transformation probability is calculated according to an optimum transformation path for transforming said example into said syntax unit.

Claim 17

Dependent Claim 17 words

A translating apparatus according to claim 16, wherein said optimum transformation path is found by dynamic programming.

Claim 18

Dependent Claim 102 words

A translating apparatus according to claim 13, wherein said word transformation probability is calculatedfurther using at least one among a word scramble probability of a word of said example unchanged or replaced with a word of said syntax unit being used with its position changed, a word copy and compound probability of a word of said example having a modifier added thereto and being used as a compound word, and a word replace and compound probability of a word of said example replaced with a word of said syntax unit having a modifier added thereto and being used as a compound word.

Claim 19

Dependent Claim 28 words

A translating apparatus according to claim 18, wherein said word transformation probability is calculated according to an optimum transformation path for transforming said example into said syntax unit.

Claim 20

Dependent Claim 104 words

A translating apparatus according to claim 19, wherein in finding said optimum transformation path instead of an actual deletion path corresponding to actually deleting a word of said example a provisional deletion path provisionally deleting a word of said example is used and instead of an actual addition path corresponding to actually adding a word of said syntax unit a provisional addition path provisionally adding a word of said syntax unit is used, further comprising word memory means for storing a provisionally deleted word and a provisionally added word provisionally deleted or added according to said provisional deletion path or said provisional addition path.

Claim 21

Dependent Claim 212 words

A translating apparatus according to claim 20, wherein a scramble path corresponding to using a word of said example unchanged or replaced with a word of said syntax unit with its position changed is selected only when either a word of said example has been stored in said word memory means as said provisionally deleted word or a word of said syntax unit has been stored in said word memory means as said provisionally added word, and thereafter said word of said example stored as said provisionally deleted word or said word of said syntax unit stored as said provisionally added word is erased from said word memory means, and a copy and compound path corresponding to a word of said example having a modifier added thereto and being used as a compound word and a replace and compound path corresponding to a word of said example replaced with a word of said syntax unit having a modifier added to it and being used as a compound word are selected only when a word to become said modifier has been stored in said word memory means as said provisionally added word, and thereafter said word to become a modifier stored as said provisionally added word is erased from said word memory means.

Claim 22

Dependent Claim 76 words

A translating apparatus according to claim 21, wherein after the end point of a transformation path transforming said example into said syntax unit is reached a provisional deletion path or a provisional adding path provisionally deleting or adding said provisionally deleted word or said provisionally added word stored in said word memory means is converted into an actual deleting path or an actual adding path respectively and the path obtained is made said optimum transformation path.

Claim 23

Dependent Claim 23 words

A translating apparatus according to claim 10, wherein said priori probability or said transformation probability is calculated on the basis of corpus data.

Claim 24

Dependent Claim 30 words

A translating apparatus according to claim 10, wherein said priori probability or said transformation probability is calculated on the basis of said examples stored in said example memory means (3).

Claim 25

Dependent Claim 129 words

A translating method for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language using example memory means (3) storing examples expressed in said first language and corresponding translations of said examples in said second language, comprising the steps of: dividing (4) said first language sentence into syntax units consisting of predetermined units of sentence structure; detecting (6) for each of said syntax units of said first language sentence an example similar to that syntax unit from among said examples; translating (7) said first language sentence in said syntax units on the basis of those of said translations corresponding to the detected examples; and generating (15) said second language sentence by compounding results of translation of said syntax units.

Claim 26

Dependent Claim 153 words

A translating method for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language using example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language, comprising the steps of: dividing (4) said first language sentence into syntax units consisting of predetermined units of sentence structure in stages from large syntax units into small syntax units and collating syntax units obtained at each stage with said examples; detecting (6) for each of said syntax units an example corresponding to that syntax unit from among said examples on the basis of results of the collation; translating (7) said first language sentence in said syntax units on the basis of those of said translations corresponding to the detected examples; and generating (15) said second language sentence by compounding results of translation of said syntax units.

Claim 27

Dependent Claim 205 words

A translating apparatus for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language, comprising: example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language; thesaurus memory means (12) storing a thesaurus wherein words are classified in a tree structure on the basis of their concepts; and calculating means (11) for calculating word similarity degrees each expressing the similarity between a word of said first language sentence and a word of one of said examples on the basis of said thesaurus (12); detecting means (6) for detecting from among said examples an example similar to said first language sentence on the basis of said word similarity degrees calculated by said calculating means; and translating means (7) for translating said first language sentence on the basis of a translation among said translations corresponding to said example detected by said detecting means, wherein said calculating means (11) calculates each of said word similarity degrees on the basis of the number of words included in a concept common to a word of said first language sentence and a word of one of said examples in said thesaurus.

Claim 28

Dependent Claim 181 words

A translating method for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language using example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language, comprising the steps of: calculating (11) word similarity degrees each expressing the similarity between a word of said first language sentence and a word of one of said examples on the basis of a thesaurus (12) wherein words are classified in a tree structure on the basis of their concepts; detecting (6) from among said examples an example similar to said first language sentence on the basis of said word similarity degrees; and translating (7) said first language sentence on the basis of a translation among said translations corresponding to said example detected; wherein each of said word similarity degrees is calculated on the basis of the number of words included in a concept common to a word of said first language sentence and a word of one of said examples in said thesaurus (12).

Claim 29

Dependent Claim 126 words

A translating apparatus for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language, comprising: example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language; detecting means (6) for detecting from among said examples an example similar to said first language sentence on the basis of a priori probability of said example being used for translating said first language sentence and a transformation probability of said example being transformed into said first language sentence and used; and translating means (7) for translating said first language sentence on the basis of a translation among said translations corresponding to said example detected by said detecting means (6).

Claim 30

Dependent Claim 39 words

A translating apparatus according to claim 29, wherein said transformation probability is calculated from a grammatical attribute transformation probability of grammatical attributes of said example being transformed and a word transformation probability of words of said example being transformed.

Claim 31

Dependent Claim 85 words

A translating apparatus according to claim 30, wherein said grammatical attribute transformation probability is calculated from a grammatical attribute copy probability of a grammatical attribute of said example being used unchanged, a grammatical attribute deletion probability of a grammatical attribute of said example being deleted, a grammatical attribute addition probability of a grammatical attribute of said first language sentence being added, and a grammatical attribute replacement probability of a grammatical attribute of said example being replaced with a grammatical attribute of said first language sentence.

Claim 32

Dependent Claim 75 words

A translating apparatus according to claim 30, wherein said word transformation probability is calculated from a word copy probability of a word of said example being used unchanged, a word deletion probability of a word of said example being deleted, a word addition probability of a word of said first language sentence being added, and a word replacement probability of a word of said example being replaced with a word of said first language sentence.

Claim 33

Dependent Claim 29 words

A translating apparatus according to claim 29, wherein said word transformation probability is calculated according to an optimum transformation path for transforming said example into said first language sentence.

Claim 34

Dependent Claim 17 words

A translating apparatus according to claim 33, wherein said optimum transformation path is found by dynamic programming.

Claim 35

Dependent Claim 105 words

A translating apparatus according to claim 32, wherein said word transformation probability is calculated further using at least one among a word scramble probability of a word of said example unchanged or replaced with a word of said first language sentence being used with its position changed, a word copy and compound probability of a word of said example having a modifier added thereto and being used as a compound word, and a word replace and compound probability of a word of said example replaced with a word of said first language sentence having a modifier added thereto and being used as a compound word.

Claim 36

Dependent Claim 29 words

A translating apparatus according to claim 32, wherein said word transformation probability is calculated according to an optimum transformation path for transforming said example into said first language sentence.

Claim 37

Dependent Claim 106 words

A translating apparatus according to claim 36, wherein in finding said optimum transformation path instead of an actual deletion path corresponding to actually deleting a word of said example a provisional deletion path provisionally deleting a word of said example is used and instead of an actual addition path corresponding to actually adding a word of said first language sentence a provisional addition path provisionally adding a word of said first language sentence is used, further comprising word memory means for storing a provisionally deleted word and a provisionally added word provisionally deleted or added according to said provisional deletion path or said provisional addition path.

Claim 38

Dependent Claim 215 words

A translating apparatus according to claim 37, wherein a scramble path corresponding to using a word of said example unchanged or replaced with a word of said first language sentence with its position changed is selected only when either a word of said example has been stored in said word memory means as said provisionally deleted word or a word of said first language sentence has been stored in said word memory means as said provisionally added word, and thereafter said word of said example stored as said provisionally deleted word or said word of said syntax unit stored as said provisionally added word is erased from said word memory means, and a copy and compound path corresponding to a word of said example having a modifier added thereto and being used as a compound word and a replace and compound path corresponding to a word of said example replaced with a word of said first language sentence having a modifier added to it and being used as a compound word are selected only when a word to become said modifier has been stored in said word memory means as said provisionally added word, and thereafter said word to become a modifier stored as said provisionally added word is erased from said word memory means.

Claim 39

Dependent Claim 77 words

A translating apparatus according to claim 38, wherein after the end point of a transformation path transforming said example into said first language sentence is reached a provisional deletion path or a provisional addition path provisionally deleting or adding said provisionally deleted word or said provisionally added word stored in said word memory means is converted into an actual deleting path or an actual addition path respectively and the path obtained is made the optimum transformation path.

Claim 40

Dependent Claim 119 words

A translating method for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language using example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language, comprising the steps of: detecting (6) from among said examples an example similar to said first language sentence on the basis of a priori probability of said example being used for translating said first language sentence and a transformation probability of said example being transformed into said first language sentence and used; and translating (7) said first language sentence on the basis of a translation among said translations corresponding to said example detected.

Claim 41

Dependent Claim 132 words

A translating apparatus for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language, comprising: example memory means (3,5) storing examples expressed in said first language and corresponding translations of said examples in said second language together with grammatical attributes of said examples; extracting means for extracting grammatical attributes of said first language sentence by carrying out syntax analysis of said first language sentence; detecting means (6) for detecting among said examples an example similar to said first language sentence taking into account grammatical attributes of said first language sentence and of said examples; and translating means (7) for translating said first language sentence on the basis of a translation among said translations corresponding to said example detected by said detecting means.

Claim 42

Dependent Claim 121 words

A translating method for translating a first language sentence expressed in a first language into a second language sentence expressed in a second language using example memory means storing examples expressed in said first language and corresponding translations of said examples in said second language and grammatical attributes of said examples, comprising the steps of: extracting grammatical attributes of said first language sentence by carrying out syntax analysis of said first language sentence; detecting (6) among said examples an example similar to said first language sentence taking into account grammatical attributes of said first language sentence and of saidexamples; and translating (7) said first language sentence on the basis of a translation among said translations which corresponds to said example detected.

Translating apparatus and translating method

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag