Exhaustive automatic processing of textual information

• US 9,633,005 B2
• Filed: 10/08/2014
• Issued: 04/25/2017
• Est. Priority Date: 10/10/2006
• Status: Active Grant

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY InfoPoisk LLC
• Inventors: Danielyan, Tatiana, Starostin, Anatoly, Zuev, Konstantin, Anisimovich, Konstantin, Selegey, Vladimir
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US14/509,492
• Publication Number:
  US 20150057992A1
• Time in Patent Office: 930 Days
• Field of Search: 704 2- 8
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• 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

Abstract

A system for natural language processing is provided. A first natural language processing program may be constructed using language-independent semantic descriptions, and language-dependent morphological descriptions, lexical descriptions, and syntactic descriptions of one or more target languages. The natural language processing program may include any of machine translation, fact extraction, semantic indexing, semantic search, sentiment analysis, document classification, summarization, big data analysis, or another program. Additional sets of natural language processing programs may be constructed.

Claims

1. A method for creating natural language processing programs, the method comprising:

receiving, by a data processor, a semantic hierarchy of language-independent semantic descriptions of a natural language, wherein the semantic hierarchy is formed by identifying semantic notions and semantic values of words associated with lexical meanings of words;

creating, by the data processor, language dependent morphological descriptions, lexical descriptions, and syntactic descriptions of one or more target languages; and

constructing, by the data processor, for the target languages, a first natural language processing program based on the language-independent semantic descriptions, the language-dependent morphological descriptions, lexical descriptions, and syntactic descriptions of the one or more target languages, wherein the first natural language processing program is based on performing syntactical and semantic analysis of natural language sentences and creating a universal representation for at least one natural language sentence, and wherein the first natural language processing program includes instructions to perform natural language processing including at least one of;

semantic analysis of the languages, semantic indexing, semantic search including multilingual semantic search, machine translation, similar document search, fact extraction, sentiment analysis, similar document search, document classification, summarization, or ediscovery.

2. The method of claim 1, further comprising constructing one or more additional natural language processing programs based on the language-independent semantic descriptions and using the language-dependent morphological descriptions, lexical descriptions, and syntactic descriptions of the target languages.

3. The method of claim 1, further comprising obtaining ontology information associated with the natural language sentences.

4. The method of claim 1, wherein the universal representation comprises a language independent semantic structure for each natural language sentence including semantic class information for each word in the natural language sentence.

5. The method of claim 4, wherein the language independent semantic structure is obtained based on exhaustive semantic-syntactic analysis.

6. A system comprising:

a memory;

one or more data processors coupled to the memory, the processors configured to perform operations comprising;

receiving a semantic hierarchy of language-independent semantic descriptions of a natural language, wherein the semantic hierarchy is formed by automatically identifying semantic notions and semantic values of words associated with lexical meanings of words;

creating language dependent morphological descriptions, lexical descriptions, and syntactic descriptions of one or more target languages; and

constructing a first natural language processing program based on the language-independent semantic descriptions, the language-dependent morphological descriptions, lexical descriptions, and syntactic descriptions of the target languages, wherein the first natural language processing program is based on performing syntactical and semantic analysis of natural language sentences and creating a universal representation for at least one natural language sentence, and wherein the first natural language processing program includes instructions to perform natural language processing including at least one of;

semantic analysis of the languages, semantic indexing, semantic search including multilingual semantic search, machine translation, similar document search, fact extraction, sentiment analysis, similar document search, document classification, summarization, or ediscovery.

7. The system of claim 6, further comprising constructing one or more additional natural language processing programs based on the universal representation.

8. The system of claim 6, further comprising obtaining ontology information associated with the natural language sentences.

9. The system of claim 6, wherein the universal representation comprises a language independent semantic structure for each natural language sentence.

10. The system of claim 9, wherein the language independent semantic structure is obtained based on exhaustive semantic-syntactic analysis.

11. The system of claim 6, wherein the first natural language program performs machine translation from a first natural language to a second natural language.

12. A non-transitory computer-readable storage medium having machine instructions stored therein, the instructions being executable by a processor to cause the processor to perform operations comprising:

receiving a semantic hierarchy of language-independent semantic descriptions of a natural language, wherein the semantic hierarchy is formed by identifying semantic notions and semantic values of words associated with lexical meanings of words;

creating language dependent morphological descriptions, lexical descriptions, and syntactic descriptions of one or more target languages; and

creating at least one ontology and establishing links of its elements with elements of the semantic hierarchy; and

constructing a first natural language processing program based on the language-independent semantic descriptions, the language-dependent morphological descriptions, lexical descriptions, and syntactic descriptions of the one or more target languages, wherein the first natural language processing program is based on performing syntactical and semantic analysis of natural language sentences and creating a universal representation for at least one natural language sentence, and wherein the first natural language processing program includes instructions to automatically perform natural language processing comprising at least one of;

semantic analysis of the languages, semantic indexing, semantic search including multilingual semantic search, machine translation, similar document search, fact extraction, sentiment analysis, similar document search, document classification, summarization, or ediscovery.