Finding an appropriate meaning of an entry in a text

• US 9,772,995 B2
• Filed: 12/24/2013
• Issued: 09/26/2017
• Est. Priority Date: 12/27/2012
• Status: Expired due to Fees

• Current Assignee: ABBYY Production LLC (ABBYY Software)
• Original Assignee: ABBYY Development LLC
• Inventors: Rylov, Alexander Gennadievich, Arkhipov, Ivan Sergeevich
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US14/654,749
• Publication Number:
  US 20150331852A1
• Time in Patent Office: 1,372 Days
• Field of Search: 704 1- 9
• 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 comprising:

performing a lexico-morphological analysis on a sentence, comprising a text entry in a text, for determining one or more meanings of one or more words in proximity to the text entry;

performing a syntactic analysis on the sentence, wherein the syntactic analysis comprises generating one or more syntactic links and associated weights between the meanings of the words in proximity to the text entry;

determining, in view of the weights associated with the syntactic links, a first meaning of the text entry; and

selecting, by one or more processing devices and in view of the determined first meaning of the text entry, a second meaning of the text entry from multiple alternative meanings provided by a dictionary entry of an electronic dictionary, wherein the dictionary entry comprises a dictionary theme for each of the alternative meanings, wherein each dictionary theme identifies one of multiple areas of human knowledge that are represented in a hierarchical structure, wherein the electronic dictionary and the hierarchical structure are stored in an electronic data storage device, and wherein selecting the second meaning comprises;

associating the first meaning of the text entry with a text theme that identifies one of the areas of human knowledge;

comparing distances between the text theme and each dictionary theme within the hierarchical structure; and

selecting, from the alternative meanings, the second meaning that has a shortest distance between the dictionary theme of the second meaning and the text theme from the distances within the hierarchical structure.

2. The method of claim 1, wherein the syntactical analysis comprises:

building a graph of generalized constituents comprising applying syntactical models; and

generating at least one syntactic tree for the sentence.

3. The method of claim 2, further comprising generating a syntactic structure with established non-tree links in view of the syntactic tree.

4. The method of claim 3, further comprising performing a semantic analysis of the sentence.

5. The method of claim 4, wherein the semantic analysis comprises determining one or more semantic links between at least one of the meanings of at least one of the words in proximity to the text entry.

6. The method of claim 5, wherein the semantic analysis comprises determining one or more weights associated with the semantic links.

7. The method of claim 6, wherein determining the first meaning of the text entry is further in view of the weights associated with the semantic links.

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

9. The method of claim 1, further comprising:

selecting a translation variant from among multiple translation variants of the text entry, wherein the translation variants correspond to the alternative meanings, and wherein the translation variant corresponds to the second meaning; and

displaying the translation variant on a screen of an electronic device.

10. A system comprising:

one or more electronic data storage devices that store instructions; and

one or more processors to execute the stored instructions to;

perform a lexica-morphological analysis on a sentence, comprising a text entry in a text, for determination of one or more meanings of one or more words in proximity to the text entry;

perform a syntactic analysis on the sentence, wherein, to perform the syntactic analysis, the processor are to generate one or more syntactic links and associated weights between the meanings of the words in proximity to the text entry;

determine, in view of the weights associated with the syntactic links, a first meaning of the text entry; and

select, in view of the determined first meaning of the text entry, a second meaning of the text entry from multiple alternative meanings provided by a dictionary entry of an electronic dictionary, wherein the dictionary entry comprises a dictionary theme for each of the alternative meanings, wherein each dictionary theme identifies one of multiple areas of human knowledge that are represented in a hierarchical structure, wherein the electronic dictionary and the hierarchical structure are stored in an electronic data storage device, and wherein, to select the second meaning, the processors are to;

associate the first meaning of the text entry with a text theme that identifies one of the areas of human knowledge;

compare distances between the text theme and each dictionary theme within the hierarchical structure; and

select, from the alternative meanings, the second meaning that has a shortest distance between the dictionary theme of the second meaning and the text theme from the distances within the hierarchical structure.

11. The system of claim 10, wherein, to perform the syntactical analysis, the processors are further to:

build a graph of generalized constituents, wherein, to build the graph, the processors are further to apply syntactical models; and

generate at least one syntactic tree for the sentence.

12. The system of claim 11, wherein the processors are further to generate a syntactic structure with established non-tree links in view of the syntactic tree.

13. The system of claim 12, wherein the processors are further to perform a semantic analysis of the sentence.

14. The system of claim 13, wherein, to perform the semantic analysis, the processors are further to determine one or more semantic links between at least one of the meanings of at least one of the words in proximity to the text entry.

15. The system of claim 14, wherein, to perform the semantic analysis, the processors are further to determine one or more weights associated with the semantic links.

16. The system of claim 15, wherein the processors are to determine the first meaning of the text entry further in view of the weights associated with the semantic links.

17. The system of claim 10, wherein, to perform the lexico-morphological analysis of the sentence, the processors are further to define possible variants of morphological form and lemma for at least one of the meanings of at least one of the words in proximity to the text entry.

18. A non-transitory computer-readable storage medium having instructions stored thereon, that when executed by one or more processing devices, cause the processing devices to:

perform a lexico-morphological analysis on a sentence, comprising a text entry in a text, for determination of one or more meanings of one or more words in proximity to the text entry;

perform a syntactic analysis on the sentence, wherein, to perform the syntactic analysis, the instructions are to cause the processing devices to generate one or more syntactic links and associated weights between the meanings of the words in proximity to the text entry;

determine, in view of the weights associated with the syntactic links, a first meaning of the text entry; and

select, by the processing devices and in view of the determined first meaning of the text entry, a second meaning of the text entry from multiple alternative meanings provided by a dictionary entry of an electronic dictionary, wherein the dictionary entry comprises a dictionary theme for each of the alternative meanings, wherein each dictionary theme identifies one of multiple areas of human knowledge that are represented in a hierarchical structure, wherein the electronic dictionary and the hierarchical structure are stored in an electronic data storage device, and wherein, to select the second meaning, the instructions are further to cause the processing devices to;

associate the first meaning of the text entry with a text theme that identifies one of the areas of human knowledge;

compare distances between the text theme and each dictionary theme within the hierarchical structure; and

select, from the alternative meanings, the second meaning that has a shortest distance between the dictionary theme of the second meaning and the text theme from the distances within the hierarchical structure.

19. The non-transitory computer-readable storage medium of claim 18, wherein, to perform the syntactical analysis, the instructions are further to cause the processing devices to:

build a graph of generalized constituents, wherein, to build the graph, the instructions are further to cause the processing devices to apply syntactical models; and

generate at least one syntactic tree for the sentence.

20. The non-transitory computer-readable storage medium of claim 19, wherein the instructions are further to cause the processing devices to generate a syntactic structure with established non-tree links in view of the syntactic tree.

21. The non-transitory computer-readable storage medium of claim 20, wherein the instructions are further to cause the processing devices to perform a semantic analysis of the sentence.

22. The non-transitory computer-readable storage medium of claim 21, wherein, to perform the semantic analysis, the instructions are further to cause the processing devices to determine one or more semantic links between at least one of the meanings of at least one of the words in proximity to the text entry.

23. The non-transitory computer-readable storage medium of claim 22, wherein, to perform the semantic analysis, the instructions are further to cause the processing devices to determine one or more weights associated with the semantic links.

24. The non-transitory computer-readable storage medium of claim 23, wherein the instructions are to cause the processing devices to determine the first meaning of the text entry further in view of the weights associated with the semantic links.

25. The non-transitory computer-readable storage medium of claim 18, wherein, to perform the lexico-morphological analysis of the sentence, the instructions are further to cause the processing devices to define possible variants of morphological form and lemma for at least one of the meanings of at least one of the words in proximity to the text entry.