Providing answers to questions using multiple models to score candidate answers

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 device and operative for:

receiving an input query;

obtaining, from an unstructured data source, a plurality of candidate answers to the input query;

producing a first score for each of the candidate answers;

sending the input query to a model selection module;

using the model selection module to select one of a plurality of scoring models based on information about the input query;

sending each of the candidate answers to the selected one of the scoring models;

using the selected one of the scoring models for weighting the first scores for the candidate answers to determine an answer score for each of the candidate answers; and

generating at least one answer to the input query based on the answer scores.

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

analyzing the input query to determine the information about the input query used to select the model.

3. The system according to claim 2 , wherein the information about the input query comprises a lexical answer type.

4. 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 device and operative for:

receiving an input query;

obtaining, from an unstructured data source, candidate answers to the input query;

producing a first score for each of the candidate answers;

using a model selection module to select for each of the candidate answers one of a plurality of scoring models based on information about the each candidate answer;

sending each of the candidate answers to the one of the scoring models selected for said each candidate answer;

using the one of the scoring models selected for each of the candidate answers for weighting the first score for the each candidate answer to determine an answer score for the each candidate answer; and

generating at least one answer to the input query based on the answer scores.

5. The system according to claim 4 , further comprising:

analyzing the candidate answer to determine the information about the candidate answer used to select the model.

6. The system according to claim 4 , wherein the information about the candidate answer comprises a part of speech.

7. An article of manufacture, comprising:

at least one tangible computer readable 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;

obtaining, from an unstructured data source, a plurality of candidate answers to the input query;

producing a first score for each of the candidate answers;

sending the input query to a model selection module;

using the model selection module to select one of a plurality of scoring models based on information about the input query;

sending each of the candidate answers to the selected one of the scoring models;

using the selected one of the scoring models for weighting the first scores for the candidate answers to determine an answer score for each of the candidate answers; and

generating at least one answer to the input query based on the answer scores.

8. The article of manufacture according to claim 7 , further comprising:

analyzing the input query to determine the information about the input query used to select the model.

9. The article of manufacture according to claim 8 , wherein the information about the input query comprises a lexical answer type.

10. An article of manufacture, comprising:

at least one tangible computer readable 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;

obtaining, from an unstructured data source, a plurality of candidate answers to the input query;

producing a first score for each of the candidate answers;

using a model selection module to select for each of the candidate answers one of a plurality of scoring models based on information about the each candidate answer;

sending each of the candidate answers to the one of the scoring models selected for said each candidate answer;

using the one of the scoring models selected for each of the candidate answers for weighting the first score for the each candidate answer to determine an answer score for the each candidate answer; and

generating at least one answer to the input query based on the answer scores.

11. The article of manufacture according to claim 10 , further comprising:

analyzing the candidate answer to determine the information about the candidate answer used to select the model.

12. The article of manufacture according to claim 11 , wherein the information about the candidate answer comprises a part of speech.