SYSTEM AND METHOD USING A DISCRIMINATIVE LEARNING APPROACH FOR QUESTION ANSWERING

• US 20090070311A1
• Filed: 09/07/2007
• Published: 03/12/2009
• Est. Priority Date: 09/07/2007
• Status: Active Grant

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Feng, Junlan
• Granted Patent: US 8,543,565 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

Disclosed are systems, methods, and computer readable media for answers to natural language questions. The method embodiment comprises training a lexical association model between a question and a first set of one or more possible answers, training a semantic association model between a question and a second set of one or more possible answers, receiving a user question containing at least one query word, parsing the user question syntactically and semantically, formulating a query from the parsed user question containing at least one query word, expanding the query based on the lexical association model and the semantic association model, weighting the at least one query word according to its importance when answering the user question, and returning an answer based on the weighted at least one query word, the lexical association model, and the semantic association model. Other features include using question-answer pairs mined to train the models and returning a plurality of answers in an order based on the lexical association model and the semantic association model.

Claims

1. A method of providing answers to natural language questions, the method comprising:

training a lexical association model between a question and a first set of one or more possible answers;

training a semantic association model between a question and a second set of one or more possible answers;

receiving a user question containing at least one query word;

parsing the user question syntactically and semantically;

formulating a query from the parsed user question containing at least one query word;

expanding the query based on the lexical association model and the semantic association model;

weighting the at least one query word according to its importance when answering the user question; and

returning an answer based on the weighted at least one query word, the lexical association model, and the semantic association model.

2. The method of claim 1, wherein question-answer pairs are used to train the lexical and semantic association models.

3. The method of claim 2, wherein the question-answer pairs are mined from the internet.

4. The method of claim 1, wherein a plurality of questions are used to train the semantic and lexical association models.

5. The method of claim 1, wherein a plurality of answers are returned.

6. The method of claim 5, wherein the plurality of answers is returned in an order based on the lexical association model and the semantic association model.

7. The method of claim 1, wherein training the lexical association model further comprises finding associated answer words for the at least one query word and building an expansion set for the at least one query word, wherein the set has one or more answer words.

8. The method of claim 7, wherein expanding the query further comprises finding a question phrase that the question begins with, locating nouns in the question phrase, and replacing the question phrase with associated named entity tags and the nouns appearing in the question phrase.

9. The method of claim 1, wherein the first set and second set of one or more possible answers are different sets.

10. The method of claim 1, wherein the first set and second set of one or more possible answers are the same set.

11. A system for providing answers to natural language questions, the system comprising:

a module configured to train a lexical association model between a question and a first set of one or more possible answers;

a module configured to train a semantic association model between a question and a second set of one or more possible answers;

a module configured to receive a user question containing at least one query word;

a module configured to parse the user question syntactically and semantically;

a module configured to formulate a query from the parsed user question containing at least one query word;

a module configured to expand the query based on the lexical association model and the semantic association model;

a module configured to weight the at least one query word according to its importance when answering the user question; and

a module configured to return an answer based on the weighted at least one query word, the lexical association model, and the semantic association model.

12. The system of claim 11, wherein question-answer pairs are used to train the lexical and semantic association models.

13. The system of claim 11, wherein a plurality of questions are used to train the semantic and lexical association models.

14. The system of claim 11, wherein a plurality of answers are returned.

15. The system of claim 14, wherein the plurality of answers is returned in an order based on the lexical association model and the semantic association model.

16. The system of claim 11, wherein training the lexical association model further comprises finding associated answer words for the at least one query word and building an expansion set for the at least one query word, wherein the set has one or more answer words.

17. The system of claim 16, wherein expanding the query further comprises finding a question phrase that the question begins with, locating nouns in the question phrase, and replacing the question phrase with associated named entity tags and the nouns appearing in the question phrase.

18. The system of claim 11, wherein the first set and second set of one or more possible answers are different sets.

19. The system of claim 11, wherein the first set and second set of one or more possible answers are the same set.

20. A computer-readable medium storing a computer program having instructions for controlling a computing device to provide answers to natural language questions, the instructions comprising:

training a lexical association model between a question and a first set of one or more possible answers;

training a semantic association model between a question and a second set of one or more possible answers;

receiving a user question containing at least one query word;

parsing the user question syntactically and semantically;

formulating a query from the parsed user question containing at least one query word;

expanding the query based on the lexical association model and the semantic association model;

weighting the at least one query word according to its importance when answering the user question; and

returning an answer based on the weighted at least one query word, the lexical association model, and the semantic association model.