Is it the right answer?

1 January 2001

conference paper
Published by Association for Computational Linguistics (ACL)

p. 425-432
https://doi.org/10.3115/1073083.1073154

Abstract

Answer Validation is an emerging topic in Question Answering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy of Web information. Experiments carried out on the TREC-2001 judged-answer collection show that the approach achieves a high level of performance ( 81% success rate). The simplicity and the efficiency of this approach make it suitable to be used as a module in Question Answering systems.

Keywords

TREC-2001 JUDGED-ANSWER COLLECTION SHOW
NOVEL APPROACH
ANSWER VALIDATION
QUESTION ANSWERING SYSTEM
QUESTION ANSWERING
IMPLICIT KNOWLEDGE
HUGE AMOUNT
WEB INFORMATION
WEB REDUNDANCY
RIGHT ANSWER
HIGH LEVEL
CANDIDATE ANSWER

This publication has 0 references indexed in Scilit: