Providing answers to questions using logical synthesis of candidate answers

• US 8,898,159 B2
• Filed: 09/22/2011
• Issued: 11/25/2014
• Est. Priority Date: 09/28/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Brown, Eric W., Chu-Carroll, Jennifer, Ferrucci, David A., Lally, Adam P., Murdock, James W. IV, Prager, John M.
• Primary Examiner(s): LE, HUNG D
• Application Number:
  US13/240,108
• Publication Number:
  US 20120078888A1
• Time in Patent Office: 1,160 Days
• Field of Search: None
• US Class Current: 707/730
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis

Abstract

A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, decomposing the input query into a plurality of different subqueries, and conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries. A ranking function is applied to each of the candidate answers to determine a ranking for each of these candidate answers; and for each of the subqueries, one of the candidate answers to the subquery is selected based on this ranking. A logical synthesis component is applied to synthesize a candidate answer for the input query from the selected the candidate answers to the subqueries. In one embodiment, the procedure applied by the logical synthesis component to synthesize the candidate answer for the input query is determined from the input query.

Claims

1. A system for generating answers to questions, comprising:

a computer device comprising at least one distinct software module, each distinct software module being embodied on a tangible computer-readable medium;

a memory; and

at least one processor coupled to the memory and operative for;

receiving an input query;

formulating a plurality of different subqueries to answer the input query, wherein each of the subqueries has an associated answer to the each subquery, and the answers to the subqueries are used to determine an answer to the input query;

conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries;

for each of the candidate answers for each of the subqueries, applying a candidate ranking function to determine a ranking for said each of the candidate answers;

for each of the subqueries, selecting one of the candidate answers to the subquery based on the ranking of said one of the candidate answers; and

applying a logical synthesis component to synthesize a candidate answer for the input query from the selected ones of the candidate answers to the subqueries.

2. The system according to claim 1, wherein the applying a logical synthesis component includes determining from the input query a procedure for synthesizing the candidate answer for the input query from the selected candidate answers to the subqueries.

3. The system according to claim 2, wherein:

the formulating a plurality of different subqueries includes decomposing the input query includes using natural language processing to decompose the input query; and

the determining the procedure for synthesizing the candidate answers includes using said natural language processing to determine said procedure when decomposing the input query.

4. The system according to claim 1, wherein the using the logical synthesis component includes using the logical synthesis component to perform a mathematical operation on data in the selected candidate answers to synthesize the candidate answer for the input query.

5. The system according to claim 1, wherein the using the logical synthesis component includes using the logical synthesis component to combine text from the selected answers to synthesize the candidate answer for the input query.

6. The system according to claim 1, wherein each of the plurality of subqueries includes text not in the input query.

7. The system according to claim 1, wherein the answers to the subqueries are numbers, and the candidate answer to the input query is determined by performing a mathematical operation on the numbers.

8. The system according to claim 1, wherein none of the answers to the subqueries is the answer to the input query.

9. An article of manufacture, comprising:

at least one tangible computer readable hardware device having computer readable program code logic tangibly embodied therein to generate answers to questions, the computer readable program code logic, when executing, performing the following;

receiving an input query;

formulating a plurality of different subqueries to answer the input query, wherein each of the subqueries has an associated answer to the each subquery, and the answers to the subqueries are used to determine an answer to the input query;

conducting a search in one or more data sources to identify at least one candidate answers to each of the subqueries;

for each of the candidate answers for each of the subqueries, applying a candidate ranking function to determine a ranking for said each of the candidate answers;

for each of the subqueries, selecting one of the candidate answers to the subquery based on the ranking of said one of the candidate answers; and

applying a logical synthesis component to synthesize a candidate answer for the input query from the selected ones of the candidate answers to the subqueries.

10. The article of manufacture according to claim 9, wherein:

the formulating a plurality of different subqueries includes decomposing the input query includes using natural language processing to decompose the input query; and

the applying a logical synthesizer includes using the natural language processing when decomposing the input query to determine a procedure for synthesizing the candidate answer for the input query from the selected candidate answers to the subqueries.

11. The article of manufacture according to claim 9, wherein the applying the ranking function includes:

for each of the candidate answers to the subqueries, producing one or more scores for said each candidate answer, and applying the ranking function to said one or more scores to determine the ranking for said each candidate answer.

12. The article of manufacture according to claim 9, wherein the using the logical synthesis component includes using the logical synthesis component to form an intersection of the selected candidate answers to synthesize the candidate answer for the input query.

13. The article of manufacture according to claim 9, wherein the using the logical synthesis component includes using the logical synthesis component to form a union of the selected candidate answers to synthesize the candidate answer for the input query.

14. A system for generating answers to questions, comprising:

a computer device comprising at least one distinct software module, each distinct software module being embodied on a tangible computer-readable medium;

a memory; and

at least one processor coupled to the memory and operative for;

receiving a plurality of input queries;

using a natural language processing to formulate a plurality of different subqueries to answer at least one of the input queries, wherein each of the subqueries has an associated answer to the at least one of the input queries, and the answers to the subqueries are used to determine an answer to the at least one of the inupt queries;

conducting a search in one or more data sources to identify candidate answers for each of the input queries, including identifying candidate answers to each of the subqueries;

for each of the candidate answers, applying a candidate ranking function to each of the candidate answers to determine a ranking for said each of the candidate answers;

applying a logical synthesis component to synthesize a resultant candidate answer for said at least one of the input queries from at least one of the candidate answers to each of the subqueries; and

applying the candidate ranking function to said resultant candidate answer to determine a ranking for said resultant candidate answer to said at least one of the input queries.

15. The method according to claim 14, wherein the applying a logical synthesis component includes determining from the input query a procedure for synthesizing the resultant candidate answer for the input query from said at least one of the candidate answers to each of the subqueries.