LANGUAGE PROCESSING DEVICE, LANGUAGE PROCESSING METHOD, AND LANGUAGE PROCESSING PROGRAM

• US 20090018821A1
• Filed: 02/09/2007
• Published: 01/15/2009
• Est. Priority Date: 02/27/2006
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Doi, Shinichi, Ando, Shinichi, Sadamasa, Kunihiko
• Granted Patent: US 8,301,435 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A language processing device includes first analysis unit 21 that subjects a natural language sentence containing a polysemic word and other words to a predetermined analysis and outputs a plurality of analysis results for the natural language sentence according to a plurality of meanings of the polysemic word, second analysis unit 23 that performs a particular analysis on the analysis results outputted from first analysis unit 21, and employs one of the analysis results, and generation unit 244 that generates a deletion rule for deleting one or more unnecessary analysis results of the first analysis unit 21 which has been deleted from the analysis results outputted from first analysis unit 21 but employed by second analysis unit 23, according to the analysis results outputted from the first analysis unit 21 and the employment result of second analysis unit 23.

Claims

1-11. -11. (canceled)

12. A language processing device comprising:

a first analysis unit that performs a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

a second analysis unit that performs a particular analysis on the plurality of analysis results outputted by said first analysis unit to adopt one analysis result from the plurality of analysis results; and

a generation unit that generates a deletion rule for deleting one or more unnecessary analysis results of said first analysis unit such that even if the one or more unnecessary analysis results are deleted from the plurality of analysis results outputted by said first analysis unit, the analysis result adopted by said second analysis unit is maintained, based on the plurality of analysis results outputted by said first analysis unit and an adopted result of said second analysis unit.

15. The language processing device according to claim 12, wherein said first analysis unit analyzes the natural language sentence in accordance with a rule-based scheme for performing an analysis based on a previously determined predetermined rule.

16. A language processing device comprising:

a knowledge base storage unit that stores a deletion rule generated by the language processing device according to claim 12;

a first analysis unit that performs a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

an ambiguity deletion unit that deletes one or more unnecessary analysis results from the plurality of analysis results outputted by said first analysis unit based on the deletion rule stored in said knowledge base storage unit; and

a second analysis unit that performs a particular analysis on the plurality of analysis results, from which the one or more unnecessary analysis results have been deleted in said ambiguity deletion unit, to adopt one analysis result from the plurality of analysis results.

19. A language processing method performed by a language processing device including a knowledge base storage unit that stores a deletion rule generated by the language processing device according to claim 12, said method comprising:

performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

deleting one or more unnecessary analysis results from the plurality of analysis results based on the deletion rule stored in said knowledge base storage unit; and

performing a particular analysis on the plurality of analysis results, from which the one or more unnecessary analysis results have been deleted, to adopt one analysis result from the plurality of analysis results.

22. A computer readable recording medium in which a language processing program is embedded, said program causing a computer to execute language processing, said computer being connected to a knowledge base storage unit that stores a deletion rule generated by the language processing device according to claim 12, said language processing comprising:

first analysis processing for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

ambiguity deletion processing for deleting one or more unnecessary analysis results from the plurality of analysis results based on the deletion rule stored in said knowledge base storage unit; and

second analysis processing for performing a particular analysis on the plurality of analysis results from which the one or more unnecessary analysis results have been deleted, to adopt one analysis result from the plurality of analysis results.

25. A language processing device comprising:

knowledge base storage means for storing a deletion rule generated by the language processing device according to claim 12;

first analysis means for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

ambiguity deletion means for deleting one or more unnecessary analysis results from the plurality of analysis results outputted by said first analysis means based on the deletion rule stored in said knowledge base storage means; and

second analysis means for performing a particular analysis on the plurality of analysis results, from which the one or more unnecessary analysis results have been deleted by said ambiguity deletion means, to adopt one analysis result from the plurality of analysis results.

13. A language processing device comprising:

a first analysis unit that performs a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

a second analysis unit that performs a particular analysis on the plurality of analysis results outputted by said first analysis unit to adopt one analysis result from the plurality of analysis results;

a storage unit that stores determination information, for each combination of one meaning of said polysemic word with information related to the other words, that indicates whether or not the combination is adopted;

an adoption information generation unit that generates adoption information, for each combination of the meaning of the polysemic word within each analysis result outputted by said first analysis unit with the information related to the other words, that indicates whether or not the combination is adopted by said second analysis unit, based on the plurality of analysis results outputted by said first analysis unit and an adopted result of said second analysis unit; and

a rule generation unit that, when the combination, which is determined as “

not adopted”

in the adoption information generated by said adoption information generation unit, corresponds to the determination information that indicates “

adopted”

in said storage unit, changes the adoption information to “

adopted” and

subsequently generates a deletion rule for deleting one or more unnecessary analysis results from the plurality of analysis results, based on the adoption information which is changed and the adoption information which is not changed.

14. The language processing device according to claim 13, wherein said combination of the meaning of the polysemic word with information related to the other words is a combination of one of the following:

a surface string, a word class, a conjugation or a combination thereof of the polysemic word with words therearound.

17. A language processing method comprising:

performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

performing a particular analysis on the plurality of analysis results to adopt one analysis result from the plurality of analysis results; and

generating a deletion rule for deleting one or more unnecessary analysis results of said performing the predetermined analysis such that even if the one or more unnecessary analysis results are deleted from the plurality of analysis results, the analysis result adopted by said performing the particular analysis is maintained, based on the plurality of analysis results outputted by said performing the predetermined analysis and an adopted result of said performing the particular analysis.

18. A language processing method performed by a language processing device including a storage unit which stores determination information, for each combination of one meaning of a polysemic word with information related to other words, that indicates whether or not the combination is adopted, said method comprising:

performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

performing a particular analysis on the plurality of analysis results to adopt one analysis result from the plurality of analysis results;

generating adoption information, for each combination of the meaning of the polysemic word within each analysis result outputted by said performing the predetermined analysis with the information related to the other words, that indicates whether or not the combination is adopted by said performing the particular analysis, based on the plurality of analysis results outputted by said performing the predetermined analysis and an adopted result of said performing the particular analysis; and

when the combination, which is determined as “

not adopted”

in the adoption information, corresponds to the determination information that indicates “

adopted”

in said storage unit, changing the adoption information to “

adopted” and

subsequently generating a deletion rule for deleting one or more unnecessary analysis results from the plurality of analysis results, based on the adoption information which is changed and the adoption information which is not changed.

20. A computer readable recording medium in which a language processing program is embedded, said program causing a computer to execute language processing comprising:

first analysis processing for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

second analysis processing for performing a particular analysis on the plurality of analysis results to adopt one analysis result from the plurality of analysis results; and

generation processing for generating a deletion rule for deleting one or more unnecessary analysis results of said first analysis processing such that even if the one or more unnecessary analysis results are deleted from the plurality of analysis results, the analysis result adopted by said second analysis processing is maintained, based on the plurality of analysis results outputted by said first analysis processing and an adopted result of said second analysis processing.

21. A computer readable recording medium in which a language processing program is embedded, said program causing a computer to execute language processing, said computer being connected to a storage unit which stores determination information, for each combination of a meaning of a polysemic word with information related to other words, that indicates whether or not the combination is adopted, said language processing comprising:

first analysis processing for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

second analysis processing for performing a particular analysis on the plurality of analysis results to adopt one analysis result from the plurality of analysis results;

adoption information generation processing for generating adoption information, for each combination of the meaning of the polysemic word within each analysis result outputted by said first analysis processing with the information related to the other words, that indicates whether or not the combination is adopted by said second analysis processing, based on the plurality of analysis results outputted by said first analysis processing and an adopted result of said second analysis processing; and

rule generation processing for, when the combination, which is determined as “

not adopted”

in the adoption information, corresponds to the determination information that indicates “

adopted”

in said storage unit, changing the adoption information to “

adopted” and

subsequently generating a deletion rule for deleting one or more unnecessary analysis results from the plurality of analysis results, based on the adoption information which is changed and the adoption information which is not changed.

23. A language processing device comprising:

first analysis means for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

second analysis means for performing a particular analysis on the plurality of analysis results outputted by said first analysis means to adopt one analysis result from the plurality of analysis results; and

generation means for generating a deletion rule for deleting one or more unnecessary analysis results of said first analysis means such that even if the one or more unnecessary analysis results are deleted from the plurality of analysis results outputted by said first analysis means, the analysis result adopted by said second analysis means is maintained, based on the plurality of analysis results outputted by said first analysis means and an adopted result of said second analysis means.

24. A language processing device comprising:

first analysis means for performing a predetermined analysis on a natural language sentence including a polysemic word and other words to output a plurality of analysis results for the natural language sentence in accordance with a plurality of meanings possessed by the polysemic word;

second analysis means for performing a particular analysis on the plurality of analysis results outputted by said first analysis means to adopt one analysis result from the plurality of analysis results;

storage means for storing determination information, for each combination of one meaning of said polysemic word with information related to the other words, that indicates whether or not the combination is adopted;

adoption information generation means for generating adoption information, for each combination of the meaning of the polysemic word within each analysis result outputted by said first analysis means with the information related to the other words, that indicates whether or not the combination is adopted by said second analysis means, based on the plurality of analysis results outputted by said first analysis means and an adopted result of said second analysis means; and

rule generation means for, when the combination, which is determined as “

not adopted”

in the adoption information generated by said adoption information generation means, corresponds to the determination information that indicates “

adopted”

in said storage means, changing the adoption information to “

adopted” and

subsequently generating a deletion rule for deleting one or more unnecessary analysis results from the plurality of analysis results, based on the adoption information which is changed and the adoption information which is not changed.