FINDING AN APPROPRIATE MEANING OF AN ENTRY IN A TEXT

• US 20150331852A1
• Filed: 12/24/2013
• Published: 11/19/2015
• Est. Priority Date: 12/27/2012
• Status: Active Grant

• Current Assignee: ABBYY Production LLC (ABBYY Software)
• Original Assignee: ABBYY Development LLC
• Inventors: Rylov, Alexander Gennadievich, Arkhipov, Ivan Sergeevich
• Granted Patent: US 9,772,995 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Disclosed are systems, computer-readable mediums, and methods for providing a meaning of an entry in a text is described. A lexico-morphological analysis is performed on the text. A syntactical analysis is performed on the text. A semantic analysis is performed on the text. A syntactical structure and a semantic structure for the entry is chosen. One or more syntactic links between each alternative meaning of words in proximity to the entry is determined. A weight is determined. One or more semantic links between each word in proximity to the entry are determined. For each semantic link, a weight associated with each semantic link is determined; and based on the weights associated with each semantic and syntactic link, determining meaning of the entry.

Claims

1. A method for providing the appropriate meaning of an entry in a text, the method comprising:

performing a lexico-morphological analysis on a sentence including the entry in the text;

performing a syntactic analysis on the sentence, wherein the syntactic analysis includes generating one or more syntactic links and associated weights between each alternative meaning and words in proximity to the entry ; and

based on the weights associated with each syntactic link, determining a meaning of the entry from the alternative meanings.

2. The method recited in claim 1, wherein the syntactical analysis includes:

detecting possible syntactic links between words in proximity to the entry in the text;

building a graph of generalized constituents;

applying syntactical models; and

generating at least one syntactic tree for the sentence including the entry.

3. The method recited in claim 2, wherein after generating at least one syntactic tree, establishing non-tree links in the tree, and selecting a syntactic structure based on the syntactic tree.

4. The method recited in claim 3, wherein after selecting a syntactic structure, performing a semantic analysis of the sentence.

5. The method recited in claim 4, wherein the semantic analysis includes determining one or more semantic links between at least one meaning of at least one word in proximity to the entry.

6. The method recited in claim 5, wherein the semantic analysis includes determining a weight associated with at least one semantic link.

7. The method recited in claim 6, wherein determining the meaning of the entry is based on the weights associated with syntactic and semantic links.

8. The method recited in claim 1, wherein the lexico-morphological analysis of the sentence includes defining possible variants of morphological form and lemma for at least one meaning of at least one word in the text in proximity to the entry.

9. The method recited in claim 1, wherein determining the meaning of the entry is based on the weights associated with syntactic links.

10. A system for providing the appropriate meaning of an entry in a text, the system comprising:

one or more processors;

computer instructions stored in one or more electronic data storage devices, that upon execution by the one of the one or more processors, cause the system to;

perform a lexico-morphological analysis on a sentence including the entry in the text;

perform a syntactic analysis on the sentence, wherein the syntactic analysis includes generating one or more syntactic links and their associated weights between each alternative meaning of words in proximity to the entry; and

based on the weights associated with each syntactic link, determine a meaning of the entry from the alternative meanings.

11. The system recited in claim 10, wherein the syntactical analysis includes:

detecting possible syntactic links between words in proximity to the entry in the text;

building a graph of generalized constituents;

applying syntactical models; and

generating at least one syntactic tree for the sentence including the entry.

12. The system recited in claim 11, wherein after generating at least one syntactic tree, establishing non-tree links in the tree, and selecting a syntactic structure based on the syntactic tree.

13. The system recited in claim 12, wherein after selecting a syntactic structure, performing a semantic analysis of the sentence.

14. The system recited in claim 13, wherein the semantic analysis includes determining one or more semantic links between at least one meaning of at least one word in proximity to the entry.

15. The system recited in claim 14, wherein the semantic analysis includes determining a weight associated with at least one semantic link.

16. The system recited in claim 15, wherein determining the meaning of the entry is based on the weights associated with syntactic and semantic links.

17. The system recited in claim 10, wherein determining the meaning of the entry is based on the weights associated with syntactic links.

18. The system recited in claim 10, wherein the lexico-morphological analysis of the sentence includes defining possible variants of morphological form and lemma for at least one meaning of at least one word in the text in proximity to the entry.

19. A non-volatile computer-readable storage medium having stored thereon a sequence of instructions, which when executed by a system, causes the system to perform steps comprising:

performing a lexico-morphological analysis on a sentence including the entry in the text;

performing a syntactic analysis on the sentence, wherein the syntactic analysis includes generating one or more syntactic links and their associated weights between each alternative meaning of words in proximity to the entry; and

based on the weights associated with each syntactic link, determining a meaning of the entry from the alternative meanings.

20. The non-volatile computer-readable storage medium recited in claim 19, wherein the syntactical analysis includes:

detecting possible syntactic links between words in proximity to the entry in the text;

building a graph of generalized constituents;

applying syntactical models; and

generating at least one syntactic tree for the sentence including the entry.

21. The non-volatile computer-readable storage medium recited in claim 20, wherein after generating at least one syntactic tree, establishing non-tree links in the tree, and selecting a syntactic structure based on the syntactic tree.

22. The non-volatile computer-readable storage medium recited in claim 21, wherein after selecting a syntactic structure, performing a semantic analysis of the sentence.

23. The non-volatile computer-readable storage medium recited in claim 22, wherein the semantic analysis includes determining one or more semantic links between at least one meaning of at least one word in proximity to the entry.

24. The non-volatile computer-readable storage medium recited in claim 23, wherein the semantic analysis includes determining a weight associated with at least one semantic link.

25. The non-volatile computer-readable storage medium recited in claim 24, wherein determining the meaning of the entry is based on the weights associated with syntactic and semantic links.

26. The non-volatile computer-readable storage medium recited in claim 19, wherein determining the meaning of the entry is based on the weights associated with syntactic links.

27. The non-volatile computer-readable storage medium recited in claim 19, wherein the lexico-morphological analysis of the sentence includes defining possible variants of morphological form and lemma for at least one meaning of at least one word in the text in proximity to the entry.