Information Extraction Supported Question Answering
Abstract
This paper discusses the use of our information extraction (IE) system, Textract, in the question-answering (QA) track of the recently held TREC-8 tests. One of our major objectives is to examine how IE can help IR (Information Retrieval) in applications like QA. Our study shows: (1) IE can provide solid support for QA; (2) low-level IE like Named Entity tagging is often a necessary component in handling most types of questions; (3) a robust natural language shallow parser provides a structural basis for handling questions; (4) high-level domain independent IE, i.e. extraction of multiple relationships and general events, is expected to bring about a breakthrough in QA.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 15, 1999
- Accession Number
- ADA460042
Entities
People
- Rohini Srihari
- Wei Li