Question answering system, data search method, and computer program

• US 20060235689A1
• Filed: 12/13/2005
• Published: 10/19/2006
• Est. Priority Date: 04/13/2005
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Masuichi, Hiroshi, Yoshimura, Hiroki, Sugihara, Daigo, Ohkuma, Tomoko
• Granted Patent: US 7,805,303 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

A question answering system includes a question input unit, a search unit, an answer candidate extraction unit, an answer candidate inspection unit and an answer output unit. The search unit executes search processing based on an input question. The answer candidate extraction unit extracts an initial answer candidate based on a result of the search processing. The answer candidate inspection unit inspects the initial answer candidate. The answer candidate inspection unit executes search processing with using a query including the initial answer candidate. The answer candidate inspection unit determines whether each word of a sentence obtained as a result of the search processing has a similar lexical meaning to that of each word of the input question. The answer candidate inspection unit selects an initial answer candidate contained in a query determined to have the similar lexical meaning, as a secondary answer candidate.

Claims

1. A question answering system comprising:

a question input unit that is input (to?) a question;

a search unit that executes search processing on a basis of the input question;

an answer candidate extraction unit that extracts an initial answer candidate on a basis of a result of the search processing executed by the search unit;

an answer candidate inspection unit that inspects the initial answer candidate extracted by the answer candidate extraction unit; and

an answer output unit that outputs a secondary answer candidate selected by the answer candidate inspection unit, wherein;

final

the answer candidate inspection unit executes search processing with using a query including the initial answer candidate extracted by the answer candidate extraction unit,

the answer candidate inspection unit determines whether or not each word of a sentence, which is obtained as a result of the search processing executed by the answer candidate inspection unit, has a similar lexical meaning to a lexical meaning of each word of the input question, and

the answer candidate inspection unit selects an initial answer candidate contained in a query, which is determined to have the similar lexical meaning, as the secondary answer candidate.

2. The question answering system according to claim 1, further comprising:

a question meaning analysis unit that extracts a question focus from the input question, wherein;

the answer candidate inspection unit generates the query including a combination of the question focus extracted by the question meaning analysis unit and the initial answer candidate extracted by the answer candidate extraction unit,

the answer candidate inspection unit selects only an initial answer candidate included in a query, with using which the answer candidate inspection unit has found a sentence through the search processing,

the answer candidate inspection unit determines whether or not each word of the found sentence has a similar lexical meaning to the lexical meaning of each word of the input question, and

the answer candidate inspection unit selects an initial answer candidate contained in the query with using which the sentence has been found, the query which is determined to have the similar lexical meaning, as the secondary answer candidate.

3. The question answering system according to claim 1, further comprising:

a question meaning analysis unit extracts a question focus and a word modifying the question focus from the input question and analyzes a lexical meaning of the word qualifying the question focus.

4. The question answering system according to claim 3, wherein the answer candidate inspection unit compares the lexical meaning of the word qualifying the question focus, which is included in the input question and is analyzed by the question meaning analysis unit, with the word of the sentence obtained as the result of the search processing executed by the answer candidate inspection unit.

5. The question answering system according to claim 3, wherein:

the question meaning analysis unit analyzes a semantic distance between the question focus and the word qualifying the question focus in a thesaurus in the analyzing of the lexical meaning of the word modifying the question focus, and

the question meaning analysis unit preferentially selects a lexical meaning having a semantic distance closer to the question focus in the meaning distance, as the lexical meaning of the word modifying the question focus.

6. The question answering system according to claim 3, wherein:

the question meaning analysis unit executes syntactic and semantic analysis processing of the input question to extract the question focus and a word modifying the question focus from the input question.

7. The question answering system according to claim 6, wherein the question meaning analysis unit extracts the question focus and a phrase portion containing a verb directly modifying the question focus from the input question with using a case frame dictionary in the syntactic and semantic analysis processing of the input question.

8. A data search method comprising:

inputting a question;

executing search processing on a basis of the input question;

extracting an initial answer candidate on a basis of a result of the search processing;

inspecting the initial answer candidate extracted to select a secondary answer candidate; and

outputting the answer candidate finally selected, wherein;

the inspecting of the initial answer candidate comprises;

executing search processing with using a query including the initial answer candidate extracted;

determining whether or not each word of a sentence, which is obtained as a result of the search processing executed with using the query including the initial answer candidate, has a similar lexical meaning to a lexical meaning of each word of the input question; and

selecting an initial answer candidate contained in a query, which is determined to have the similar lexical meaning, as the secondary answer candidate.

9. The data search method according to claim 8, further comprising:

extracting a question focus from the input question, wherein;

the inspecting of the initial answer candidate comprises;

generating the query including a combination of the question focus extracted and the initial answer candidate extracted;

selecting only an initial answer candidate included in a query, with using which a sentence has been found through the search processing;

determining whether or not each word of the found sentence has a similar lexical meaning to the lexical meaning of each word of the input question; and

selecting an initial answer candidate contained in the query with using which the sentence has been found, the query which is determined to have the similar lexical meaning, as the secondary answer candidate.

10. The data search method according to claim 8, further comprising:

extracting a question focus and a word modifying the question focus from the input question; and

analyzing a lexical meaning of the word qualifying the question focus.

11. The data search method according to claim 10, wherein

the inspecting of the initial answer candidate further comprising comparing the lexical meaning of the word qualifying the question focus, which is included in the input question and is analyzed, with the word of the sentence obtained as the result of the search processing executed in the inspecting of the initial answer candidate.

12. The data search method according to claim 10, wherein

the analyzing of the lexical meaning of the word modifying the question focus comprises:

analyzing a semantic distance between the question focus and the word qualifying the question focus in a thesaurus; and

preferentially selecting a lexical meaning having a semantic distance closer to the question focus in the meaning distance, as the lexical meaning of the word modifying the question focus.

13. The data search method according to claim 10 wherein the analyzing of the lexical meaning of the word modifying the question focus executes syntactic and semantic analysis processing of the input question to extract the question focus and a word modifying the question focus from the input question.

14. The data search method according to claim 13, wherein the analyzing of the lexical meaning of the word modifying the question focus further extracts the question focus and a phrase portion containing a verb directly modifying the question focus from the input question with using a case frame dictionary in the syntactic and semantic analysis processing of the input question.

15. A computer program stored in a recording medium, the computer program causing a computer to execute data search processing comprising:

inputting a question;

executing search processing on a basis of the input question;

extracting an initial answer candidate on a basis of a result of the search processing;

inspecting the initial answer candidate extracted to select a secondary answer candidate; and

outputting the answer candidate finally selected, wherein;

the inspecting of the initial answer candidate comprises;

executing search processing with using a query including the initial answer candidate extracted;

determining whether or not each word of a sentence, which is obtained as a result of the search processing executed with using the query including the initial answer candidate, has a similar lexical meaning to a lexical meaning of each word of the input question; and

selecting an initial answer candidate contained in a query, which is determined to have the similar lexical meaning, as the secondary answer candidate.