Book chapter
QUERY MODULATION FOR WEB-BASED QUESTION ANSWERING
Advances in Open Domain Question Answering, pp.285-303
Text Speech and Language Technology, Springer Nature
2008
DOI: 10.1007/978-1-4020-4746-6_9
Abstract
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In this paper, we study how we can effectively use these existing search engines to mine the Web and discover the "correct" answers to factual natural language questions. We propose a probabilistic algorithm called QASM (Question Answering using Statistical Models) that learns the best query paraphrase of a natural language question. We validate our approach for both local and web search engines using questions from the TREC evaluation.
Details
- Title: Subtitle
- QUERY MODULATION FOR WEB-BASED QUESTION ANSWERING
- Creators
- Dragomir R. Radev - University of Michigan–Ann ArborHong QiZhiping ZhengSasha Blair-Goldensohn - Columbia UniversityZhu Zhang - University of ArizonaWeiguo Fan - Virginia Polytech Inst & State Univ, Blacksburg, VA 24061 USAJohn Prager - IBM
- Contributors
- T Strzalkowski (Editor)S Harabagiu (Editor)
- Resource Type
- Book chapter
- Publication Details
- Advances in Open Domain Question Answering, pp.285-303
- Publisher
- Springer Nature; NEW YORK
- Series
- Text Speech and Language Technology
- DOI
- 10.1007/978-1-4020-4746-6_9
- ISSN
- 1386-291X
- Number of pages
- 19
- Language
- English
- Date published
- 2008
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380588002771
Metrics
12 Record Views