Title

Syntax-Based Concept Extraction For Question Answering Using Semex

Abstract

The SEMEX tool tor question answering is presented. Its architecture and features for extracting from input text a network of concept nodes that index syntax-based logical forms, are described. Methods are shown for decomposing questions into boolean combinations of question patterns and for using the concept network and logical forms together with WordNet for question answering. SEMEX's encouraging performance against the TREC 2005 question answering test set is discussed. Compilation copyright © 2006. American Association for Artificial Intelligence (www.aaai.org). All rights reserved.

Publication Date

7-24-2006

Publication Title

FLAIRS 2006 - Proceedings of the Nineteenth International Florida Artificial Intelligence Research Society Conference

Volume

2006

Number of Pages

789-790

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

33746037568 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/33746037568

This document is currently not available here.

Share

COinS