Conference proceeding
Probabilistic question answering on the web
Proceedings of the 11th international conference on world wide web, pp.408-419
WWW '02
05/07/2002
DOI: 10.1145/511446.511500
Abstract
Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage extraction, phrase extraction, and answer ranking. In this paper we describe some probabilistic approaches to the last three of these stages. We show how our techniques apply to a number of existing search engines and we also present results contrasting three different methods for question answering. Our algorithm, probabilistic phrase reranking (PPR) using proximity and question type features achieves a total reciprocal document rank of .20 on the TREC 8 corpus. Our techniques have been implemented as a Web-accessible system, called NSIR.
Details
- Title: Subtitle
- Probabilistic question answering on the web
- Creators
- Dragomir Radev - University of Michigan–Ann ArborWeiguo Fan - University of Michigan–Ann ArborHong Qi - University of Michigan–Ann ArborHarris Wu - University of Michigan–Ann ArborAmardeep Grewal - University of Michigan–Ann Arbor
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of the 11th international conference on world wide web, pp.408-419
- Publisher
- ACM
- Series
- WWW '02
- DOI
- 10.1145/511446.511500
- Language
- English
- Date published
- 05/07/2002
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380445002771
Metrics
1 Record Views