Systems for translating sentences between languages using language-independent semantic structures and ratings of syntactic constructions

• US 8,214,199 B2
• Filed: 03/22/2007
• Issued: 07/03/2012
• Est. Priority Date: 10/10/2006
• Status: Active Grant

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY Software
• Inventors: Anismovich, Konstantin, Selegey, Vladimir, Zuev, Konstantin
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): ROBERTS, SHAUN A
• Application Number:
  US11/690,104
• Publication Number:
  US 20080086299A1
• Time in Patent Office: 1,930 Days
• Field of Search: 704 1- 10
• US Class Current: 704/4
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

A method and computer system for translating sentences between languages from an intermediate language-independent semantic representation is provided. On the basis of comprehensive understanding about languages and semantics, exhaustive linguistic descriptions are used to analyze sentences, to build syntactic structures and language independent semantic structures and representations, and to synthesize one or more sentences in a natural or artificial language. A computer system is also provided to analyze and synthesize various linguistic structures and to perform translation of a wide spectrum of various sentence types. As result, a generalized data structure, such as a semantic structure, is generated from a sentence of an input language and can be transformed into a natural sentence expressing its meaning correctly in an output language. The method and computer system can be applied to in automated abstracting, machine translation, natural language processing, control systems, Internet information retrieval, etc.

Claims

1. A computer system adapted to synthesize a sentence into an output language, the computer system comprising:

a lexical synthesizer adapted to perform a lexical selection on a language-independent semantic structure of the sentence using semantic descriptions and lexical descriptions of the output language, wherein the lexical synthesizer is adapted to apply semantic structure correction rules to the language-independent semantic structure to overcome asymmetries between the language-independent semantic structure and the syntactic structure of the sentence in the output language, and wherein the semantic descriptions and the lexical descriptions of the output language are combined into lexical-semantic descriptions;

a surface structure builder adapted to build a surface structure of an output sentence in the output language from the language-independent semantic structure using syntactic descriptions and morphological descriptions of the output language, wherein the surface structure of the output sentence is built at least in part based on ratings of syntactic constructions for elements of the source sentence;

a morphological synthesizer adapted to perform a morphological synthesis on the surface structure of the output sentence in the output language using morphological descriptions of the output language and to construct the output sentence in the output language; and

a linear order synthesizer adapted to determine a linear order for and restore movements on the syntactic structure of the output sentence in the output language.

2. The computer system of claim 1, wherein the morphological synthesis is performed on lexical meanings of constituent cores of the surface structure of the output sentence in the output language.

3. The computer system of claim 1, wherein the one or more semantic structure correction rules include one or more semantemes calculating rules or one or more normalization rules for transforming the structure of the output sentence.

4. The computer system of claim 1, wherein obtaining a language-independent semantic structure to represent the meaning of the sentence includes (1) performing a rough syntactic analysis on the sentence to generate a graph of generalized constituents and (2) performing a precise syntactic analysis on the graph of the generalized constituents to generate one or more syntactic trees to represent the sentence from the graph of the generalized constituents.

5. The computer system of claim 1, wherein applying semantic structure correction rules to the language-independent semantic structure to overcome asymmetries includes the use of semanteme calculating rules and semanteme normalization rules to remove asymmetries.

6. The computer system of claim 1, wherein the syntactic structure of the sentence includes deep slots and lexical meanings, wherein the language-independent semantic structure is generated by:

(1) substituting each lexical meaning of the sentence in the source language with a corresponding language-independent semantic class, (2) confirming a linear order of lexical meanings, and (3) after the linear order is confirmed, deleting surface slots when generating the language-independent semantic structure, and wherein only deep slots and deep slot descriptions are used to build the language-independent semantic structure of the sentence.

7. A computer system adapted to translate the meanings of a source sentence from an input language into an output language, comprising:

a source sentence analyzer adapted to analyze meanings of the source sentence using linguistic descriptions of the source language and to construct a language-independent semantic structure to represent the meanings of the source sentence; and

an output sentence synthesizer adapted to synthesize an output sentence to represent the meanings of the source sentence in an output language from the language-independent semantic structure using information from linguistic descriptions of the output language, wherein the output sentence synthesizer comprises a linear order synthesizer adapted to determine a linear order for and restore movements on the syntactic structure of the output sentence in the output language, wherein the output sentence analyzer is adapted to apply semantic structure correction rules to the language-independent semantic structure to overcome asymmetries between the language-independent semantic structure and the syntactic structure of the output sentence in the output language, wherein a surface structure of the output sentence is built at least in part based on ratings of syntactic constructions for elements of the source sentence, and wherein applying semantic structure correction rules to the language-independent semantic structure to overcome asymmetries includes the use of semanteme calculating rules and semanteme normalization rules to remove asymmetries.

8. The computer system of claim 7, wherein the source analyzer further comprises a lexical-morphological analyzer adapted to perform a lexical analysis and a lexical-morphological analysis on each element of the source sentence and generating a lexical-morphological structure of the source sentence.

9. The computer system of claim 7, wherein the source analyzer further comprises a rough syntactic analyzer adapted to perform a rough syntactic analysis on the lexical-morphological structure of the source sentence and generate a graph of generalized constituents from the lexical-morphological structure of the source sentence.

10. The computer system of claim 9, wherein the source analyzer further comprises a precise syntactic analyzer adapted to perform a precise syntactic analysis on the graph of the generalized constituents and generate a syntactic structure of the source sentence from the graph of the generalized constituents.

11. The computer system of claim 7, wherein the source analyzer further comprises a semantic analyzer adapted to perform a semantic analysis on the syntactic structure of the source sentence and generate the language-independent semantic structure for the source sentence.

12. The computer system of claim 7, wherein the output synthesizer further comprises a lexical synthesizer adapted to perform a lexical selection on the language-independent semantic structure using the lexical descriptions of the output language and the semantic descriptions.

13. The computer system of claim 7, wherein the output synthesizer further comprises a surface structure builder adapted to build a surface structure from the language-independent semantic structure using syntactic descriptions and the lexical descriptions of the output language.

14. The computer system of claim 7, wherein the output synthesizer further comprises a linear order synthesizer adapted to determine a linear order and restoring movements on the syntactic structure of the output sentence in the output language.

15. The computer system of claim 7, wherein the output synthesizer further comprises a morphological synthesizer adapted to perform a morphological synthesis on the surface structure using morphological descriptions of the output language and construct the output sentence in the output language.

16. The computer system of claim 15, wherein the morphological synthesis is performed on lexical meanings of constituent cores of the surface structure.

17. The computer system of claim 7, wherein the output language comprises a natural language selected from the group consisting of English, French, German, Italian, Russian, Spanish, Ukrainian, Dutch, Danish, Swedish, Finnish, Portuguese, Slovak, Polish, Czech, Hungarian, Lithuanian, Latvian, Estonian, Greek, Bulgarian, Turkish, Tatar, Hindi, Serbian, Croatian, Romanian, Slovenian, Macedonian, Japanese, Korean, Chinese, Arabic, Hebrew, and Swahili.

18. A computer system adapted to represent a source sentence from a source language into an output sentence in an output language, the computer system comprising:

a lexical-morphological analyzer adapted to perform a lexical analysis and a lexical-morphological analysis on each element of the source sentence to generate a lexical-morphological structure of the source sentence;

a syntactic analyzer adapted to perform a syntactic analysis on the lexical-morphological structure of the source sentence;

a semantic analyzer adapted to perform a semantic analysis on the source sentence and generate a language-independent semantic structure for the source sentence;

a lexical synthesizer adapted to perform a lexical selection on the language-independent semantic structure of the source sentence using lexical descriptions of the output language and semantic descriptions, wherein the lexical synthesizer is adapted to combined the semantic descriptions and the lexical descriptions of the output language into lexical-semantic descriptions;

a surface structure builder adapted to build a surface structure of the output sentence in the output language from the language-independent semantic structure using syntactic descriptions and the lexical descriptions of the output language and construct the output sentence in the output language, wherein the surface structure of the output sentence in the output language is built at least in part based on ratings of syntactic constructions for elements of the source sentence; and

a linear order synthesizer adapted to determine a linear order for and restore movements on the syntactic structure of the output sentence in the output language.

19. The computer system of claim 18, further comprising:

a morphological synthesizer adapted to perform a morphological synthesis on the surface structure of the output sentence in the output language using morphological descriptions of the output language and synthesize the output sentence.

20. A computer system adapted to synthesize a sentence into an output sentence in an output language, the computer system comprising:

a lexical synthesizer adapted to perform a lexical selection on a language-independent semantic structure of the sentence using lexical descriptions of the output language and semantic descriptions, wherein the lexical synthesizer is adapted to apply semantic structure correction rules to the language-independent semantic structure to overcome asymmetries between the language-independent semantic structure and a syntactic structure of the output sentence in the output language, wherein the lexical synthesizer combines the semantic descriptions and the lexical descriptions of the output language into lexical-semantic descriptions;

a surface structure builder adapted to build a surface structure of the output sentence in the output language from the language-independent semantic structure using syntactic descriptions and lexical descriptions of the output language, the syntactic descriptions and the lexical descriptions being taken from the combined lexical-semantic descriptions, wherein the surface structure of the output sentence in the output language is built at least in part based on ratings of syntactic constructions for elements of the source sentence;

a linear order synthesizer adapted to determine a linear order for and restore movements on the syntactic structure; and

a morphological synthesizer adapted to perform a morphological synthesis on the surface structure of the output sentence in the output language using morphological descriptions of the output language and construct the sentence in the output language.