Automated question answering in Webclopedia: a demonstration

Authors:
Ulf Hermjakob;Eduard Hovy;Chin-Yew Lin
Affiliations:
USC Information Sciences Institute, Marina del Rey, CA;USC Information Sciences Institute, Marina del Rey, CA;USC Information Sciences Institute, Marina del Rey, CA
Venue:
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Year:
2002

Citing 3
Cited 1

Learning parse and translation decisions from examples with rich context

Learning parse and translation decisions from examples with rich context
Toward semantics-based answer pinpointing

HLT '01 Proceedings of the first international conference on Human language technology research
A question/answer typology with surface text patterns

HLT '02 Proceedings of the second international conference on Human Language Technology Research

From symbolic to sub-symbolic information in question classification

Artificial Intelligence Review

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this demonstration we present work in our Webclopedia (Hovy et al. 2000, 2001) project on semantics-based answer pinpointing. Through a live interface, users can type in their questions in the query window or select a TREC10 question (Figure 1). The system will then parse the question and return the top 5 answers (Figure 1).