SYSTEM AND METHOD FOR FINDING THE MOST LIKELY ANSWER TO A NATURAL LANGUAGE QUESTION

• US 20080201132A1
• Filed: 04/28/2008
• Published: 08/21/2008
• Est. Priority Date: 11/15/2000
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Brown, Eric W., Coden, Anni R., Prager, John Martin, Radev, Dragomir Radkov, Samn, Valerie
• Granted Patent: US 8,340,955 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Automated question answering is disclosed that relates to the selection of an answer to a question from a pool of potential answers which awe manually or automatically extracted from a large collection of textual documents. The a feature extraction component, a feature combination component, an answer selection component, and an answer presentation component, among others, are included. The input to the system is a set of one or more natural language questions and a collection of textual document The output is a (possibly ranked) set of factual answers to the questions, these answers being extracted from the document collection.

Claims

1. A method for selecting answers to natural language questions from a collection of textual documents comprising the steps of:

extracting scoring features from a candidate list of passages of possible answers, wherein said scoring feature is a number of words in a candidate answer that are different than words in said natural language question;

scoring the possible answers using the extracted scoring features and a features scoring function; and

presenting the best scoring possible answer to the user with context from the passage containing the answer.

2. A method as in claim 1, wherein the feature scoring function is a linear combination of weighted features.

3. A method as in claim 2, wherein the parameters of the scoring function are manually determined.

4. A method as in claim 2, wherein the parameters of the scoring function are learned by a machine learning algorithm.

5. A method as in claim 1, wherein the candidate list of passages of possible answers is obtained from the collection of documents using an information retrieval engine.

6. A method for selecting answers to natural language questions from a collection of textual documents comprising the steps of:

extracting scoring features from a candidate list of passages of possible answers, wherein said scoring feature is an average distance between the beginning of a candidate answer in a passage and words in said natural language question that appear in said passage, and wherein said average distance is measured in a count of words;

scoring the possible answers using the extracted scoring features and a features scoring function; and

presenting the best scoring possible answer to the user with context from the passage containing the answer.

7. A method as in claim 6, wherein the feature scoring function is a lineal combination of weighted features.

8. A method as in claim 7, wherein the parameters of the scoring function are manually determined.

9. A method as in claim 7, wherein the parameters of the scoring function are learned by a machine learning algorithm

10. A method as in claim 6, wherein the candidate list of passages of possible answers is obtained from the collection of documents using an information retrieval engine.

11. A system for selecting answers to natural language questions from a collection of textual documents, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

extract scoring features from a candidate list of passages of possible answers, wherein said scoring feature is a number of words in a candidate answer that are different than words in said natural language question;

score the possible answers using the extracted scoring features and a features scoring function; and

present the best scoring possible answer to the user with context from the passage containing the answer.

12. A system as in claim 11, wherein the feature scoring function is a linear combination of weighted features.

13. A system as in claim 12, wherein the parameters of the scoring function are manually determined.

14. A system as in claim 12, wherein the parameters of the scoring function are learned by a machine learning algorithm.

15. A system as in claim 11, wherein the candidate list of passages of possible answers is obtained from the collection of documents using an information retrieval engine.

16. A system for selecting answers to natural language questions from a collection of textual documents, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

extract scoring features from a candidate list of passages of possible answers, wherein said scoring feature is an average distance between the beginning of a candidate answer in a passage and words in said natural language question that appear in said passage, and wherein said average distance is measured in a count of words;

score the possible answers using the extracted scoring features and a features scoring function; and

present the best scoring possible answer to the user with context from the passage containing the answer.

17. A system as in claim 16, wherein the feature scoring function is a linear combination of weighted features

18. A system as in claim 17, wherein the parameters of the scoring function are manually determined.

19. A system as in claim 17, wherein the parameters of the scoring function are learned by a machine learning algorithm

20. A system as in claim 16, wherein the candidate list of passages of possible answers is obtained from the collection of documents using an information retrieval engine.

21. An article of manufacture for selecting answers to natural language questions from a collection of textual documents, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

extracting scoring features from a candidate list of passages of possible answers, wherein said scoring feature is a number of words in a candidate answer that are different than words in said natural language question;

scoring the possible answers using the extracted scoring features and a features scoring function; and

presenting the best scoring possible answer to the user with context from the passage containing the answer.

22. A article of manufacture for selecting answers to natural language questions from a collection of textual documents, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

extracting scoring features from a candidate list of passages of possible answers, wherein said scoring feature is an average distance between the beginning of a candidate answer in a passage and words in said natural language question that appear in said passage, and wherein said average distance is measured in a count of words;

scoring the possible answers using the extracted scoring features and a features scoring function; and

presenting the best scoring possible answer to the user with context from the passage containing the answer.