METHOD FOR TEXT PROCESSING

• US 20160232142A1
• Filed: 10/23/2015
• Published: 08/11/2016
• Est. Priority Date: 08/29/2014
• Status: Active Grant

• Current Assignee: YE Hub Armenia LLC
• Original Assignee: Yandex Europe AG (Yandex N.V.)
• Inventors: MELNIKOV, Ilia Alekseevich
• Granted Patent: US 9,898,448 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

Method for text processing executable at a computing device, comprising appreciating a source phrase comprised of source words; appreciating a target phrase comprised of target words; associating a respective source word feature set with each one of the source words; associating a respective target word feature set with each one of the target words; analyzing source word feature sets and target word feature sets; and based on the analysis, generating one or more phrase transformation rules for transforming the source phrase into the target phrase. Also a server and non-transitory computer-readable medium storing program instructions for carrying out the method.

Claims

1. A computer-implemented method for text processing, the method being executable at a computing device, the method comprising:

acquiring a source phrase comprised of source words;

acquiring a target phrase comprised of target words;

associating a respective source word feature set with each one of the source words;

associating a respective target word feature set with each one of the target words;

analyzing the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words;

based on the mapping, generating one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase;

acquiring a text phrase; and

applying the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.

2. The method of claim 1, wherein analyzing the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words comprises determining a similarity of each one of the source word feature sets to each one of the target word feature sets.

3. The method of claim 2, wherein:

each one of the source word feature sets includes one or more grammatical features of the source word with which that source word feature set is associated;

each one of the target word feature sets includes one or more grammatical features of the target word with which that target word feature set is associated; and

determining the similarity of each one of the source word feature sets to each one of the target word feature sets comprises comparing the respective grammatical features of each one of the source words to the respective grammatical features of each one of the target words.

4. The method of claim 2, wherein:

each one of the source word feature sets includes a meaning of the source word with which that source word feature set is associated;

each one of the target word feature sets includes a meaning of the target word with which that target word feature set is associated; and

determining the similarity of each one of the source word feature sets to each one of the target word feature sets comprises determining a similarity of the respective meaning of each one of the source words to the respective meaning of each one of the target words.

5. The method of claim 2, wherein:

analyzing the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words further comprises selecting a most similar one of the target word feature sets to one of the source word feature sets; and

generating the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generating a first phrase transformation rule applicable to the source phrase to transform a source word associated with the one of the source word feature sets into a target word associated with the most similar one of the target word feature sets.

6. The method of claim 5, wherein:

the source word associated with the one of the source word feature sets and the target word associated with the most similar one of the target word feature sets share a same root; and

the first phrase transformation rule is applicable to the source phrase to modify a form of the source word to a form of the target word.

7. The method of claim 1, wherein generating the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generating a second phrase transformation rule applicable to the source phrase to delete at least one word from the source phrase.

8. The method of claim 1, wherein generating the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generating a third phrase transformation rule applicable to the source phrase to add at least one word to the source phrase.

9. The method of claim 1, further comprising:

receiving a text phrase; and

applying the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.

10. The method of claim 9, wherein the text phrase differs from the source phrase, and the method further comprises, before applying the one or more phrase transformation rules to the text phrase, determining that a similarity of the text phrase to the source phrase is greater than a threshold.

12. The method of claim 10, wherein determining that the similarity of the text phrase to the source phrase is greater than the threshold comprises performing at least one of a grammatical analysis and a semantic analysis of the text phrase and the source phrase.

11. A method for text processing, the method being executable at a computing device comprising a memory, the memory storing one or more phrase transformation rules having been generated based on an analysis of feature sets including a source word feature set associated with a source word of a source phrase and a target word feature set associated with a target word of a target phrase, the method comprising:

acquiring a text phrase;

determining that a similarity of the text phrase to the source phrase is greater than a threshold; and

applying the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.

13. A non-transitory computer-readable medium storing program instructions for text processing, the program instructions being executable by a computing device to effect:

acquisition of a source phrase comprised of source words;

acquisition of a target phrase comprised of target words;

association of a respective source word feature set with each one of the source words;

association of a respective target word feature set with each one of the target words;

analysis of the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words;

based on the mapping, generation of one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase;

acquisition a text phrase; and

applying the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.

14. The medium of claim 13, wherein analysis of the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words comprises determination of a similarity of each one of the source word feature sets to each one of the target word feature sets.

15. The medium of claim 14, wherein:

each one of the source word feature sets includes one or more grammatical features of the source word with which that source word feature set is associated;

each one of the target word feature sets includes one or more grammatical features of the target word with which that target word feature set is associated; and

determination of the similarity of each one of the source word feature sets to each one of the target word feature sets comprises comparison of the respective grammatical features of each one of the source words to the respective grammatical features of each one of the target words.

16. The medium of claim 14, wherein:

each one of the source word feature sets includes a meaning of the source word with which that source word feature set is associated;

each one of the target word feature sets includes a meaning of the target word with which that target word feature set is associated; and

determination of the similarity of each one of the source word feature sets to each one of the target word feature sets comprises determination of a similarity of the respective meaning of each one of the source words to the respective meaning of each one of the target words.

17. The medium of claim 14, wherein:

analysis of the source word feature sets and the target word feature sets to determine a mapping from the source words to the target words further comprises selection of a most similar one of the target word feature sets to one of the source word feature sets; and

generation of the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generation of a first phrase transformation rule applicable to the source phrase to transform a source word associated with the one of the source word feature sets into a target word associated with the most similar one of the target word feature sets.

18. The medium of claim 17, wherein:

the source word associated with the one of the source word feature sets and the target word associated with the most similar one of the target word feature sets share a same root; and

the first phrase transformation rule is applicable to the source phrase to modify a form of the source word to a form of the target word.

19. The medium of claim 15, wherein generation of the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generation of a second phrase transformation rule applicable to the source phrase to delete at least one word from the source phrase.

20. The medium of claim 15, wherein generation of the one or more phrase transformation rules applicable to the source phrase to transform the source phrase into the target phrase comprises generation of a third phrase transformation rule applicable to the source phrase to add at least one word to the source phrase.

21. The medium of claim 15, wherein the program instructions are executable to further effect:

acquisition of a text phrase; and

application of the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.

22. The medium of claim 21, wherein the text phrase differs from the source phrase, and the program instructions are executable to further effect, before application of the one or more phrase transformation rules to the text phrase, determination that a similarity of the text phrase to the source phrase is greater than a threshold.

24. The medium of claim 22, wherein determination that the similarity of the text phrase to the source phrase is greater than the threshold comprises performance of at least one of a grammatical analysis and a semantic analysis of the text phrase and the source phrase.

23. A non-transitory computer-readable medium storing one or more phrase transformation rules and program instructions, the one or more phrase transformation rules having been generated based on an analysis of feature sets including a source word feature set associated with a source word of a source phrase and a target word feature set associated with a target word of a target phrase, the program instructions, the program instructions executable by a computing device to effect:

receiving of a text phrase;

determination that a similarity of the text phrase to the source phrase is greater than a threshold; and

application of the one or more phrase transformation rules to the text phrase to generate a transformed text phrase.