A question answering system supported by information extraction
Open Access
- 1 January 2000
- proceedings article
- Published by Association for Computational Linguistics (ACL)
- p. 166-172
- https://doi.org/10.3115/974147.974170
Abstract
This paper discusses an information extraction (IE) system, Textract, in natural language (NL) question answering (QA) and examines the role of IE in QA application. It shows: (i) Named Entity tagging is an important component for QA, (ii) an NL shallow parser provides a structural basis for questions, and (iii) high-level domain independent IE can result in a QA breakthrough.This publication has 0 references indexed in Scilit: