Example-based translation method and system employing multi-stage syntax dividing
First Claim
1. 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 storing examples expressed in said first language and corresponding translations of said examples in said second language;
dividing means for dividing said first language sentence into syntax units consisting of predetermined units of sentence structure;
detecting means 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 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; and
generating means for generating said second language sentence by compounding results of translation of said syntax units obtained by said translating means, wherein said dividing means divides said first language sentence into large syntax units and when none of said examples is similar to any of said large syntax units, divides said large syntax units into smaller syntax units.
0 Assignments
0 Petitions
Accused Products
Abstract
A translating apparatus and a translating method wherein a first language sentence is divided into syntax units consisting of predetermined units of sentence structure such as clauses and phrases in stages from large syntax units into small syntax units and at each stage stored examples most similar to these syntax units are detected using probability models taking into account grammatical attributes of the syntax units and of the examples and using generalized linguistic knowledge and with reference to a thesaurus and the syntax units are translated on the basis of these detected examples and the results of translation of the syntax units are compounded to generate a second language sentence. The invention makes it possible to carry out high-quality translating efficiently and therefore at a high processing speed while eliminating the need for many superficially different examples having the same meaning content to be prepared and the need for the thesaurus to be regularly structured or have uniform distances between concepts.
-
Citations
14 Claims
-
1. 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 storing examples expressed in said first language and corresponding translations of said examples in said second language;
dividing means for dividing said first language sentence into syntax units consisting of predetermined units of sentence structure;
detecting means 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 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; and
generating means for generating said second language sentence by compounding results of translation of said syntax units obtained by said translating means, wherein said dividing means divides said first language sentence into large syntax units and when none of said examples is similar to any of said large syntax units, divides said large syntax units into smaller syntax units. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. 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, comprising the steps of:
-
dividing said first language sentence into syntax units consisting of predetermined units of sentence structure;
detecting for each of said syntax units of said first language sentence an example similar to that syntax unit from among said examples;
translating said first language sentence in said syntax units on the basis of those of said translations corresponding to the detected examples; and
generating said second language sentence by compounding results of translation of said syntax units, wherein said dividing step first divides said first language sentence into large syntax units and when none of said examples is similar to any of said large syntax units, subsequently divides said large syntax units into smaller syntax units.
-
-
10. 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, comprising the steps of:
-
dividing 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 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 said first language sentence in said syntax units on the basis of those of said translations corresponding to the detected examples; and
generating said second language sentence by compounding results of translation of said syntax units, wherein said dividing step first divides said first language sentence into large syntax units and when none of said examples corresponds to any of said large syntax units, subsequently divides said large syntax units into smaller syntax units.
-
-
11. 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 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 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 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 syntax analysis includes dividing said first language sentence into large syntax units and when none of said examples is similar to said first language sentence, said syntax analysis includes dividing said large syntax units into smaller syntax units.
- example memory means storing examples expressed in said first language and corresponding translations of said examples in said second language together with grammatical attributes of said examples;
-
12. 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 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 said first language sentence on the basis of a translation among said translations which corresponds to said example detected, wherein said syntax analysis includes dividing said first language sentence into large syntax units and when none of said examples is similar to said first language sentence, said syntax analysis includes dividing said large syntax units into smaller syntax units.
-
-
13. 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 storing examples expressed in said first language and corresponding translations of said examples in said second language;
thesaurus memory means storing a thesaurus wherein words are classified in a tree structure on the basis of their concepts; and
calculating means 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;
detecting means 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 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 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 expressed in said first language in said thesaurus.
-
-
14. 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, comprising the steps of:
-
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 a thesaurus wherein words are classified in a tree structure on the basis of their concepts;
detecting from among said examples an example similar to said first language sentence on the basis of said word similarity degrees; and
translating 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 expressed in said first language in said thesaurus.
-
Specification