Methods for Using Textual Entailment in Open-Domain Question Answering

DMCA

Methods for Using Textual Entailment in Open-Domain Question Answering (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by A Harabagiu , Andrew Hickl

Venue:	In Proceedings of ACL 2006
Citations:	55 - 2 self

BibTeX

@INPROCEEDINGS{Harabagiu06methodsfor,
    author = {A Harabagiu and Andrew Hickl},
    title = {Methods for Using Textual Entailment in Open-Domain Question Answering},
    booktitle = {In Proceedings of ACL 2006},
    year = {2006},
    pages = {905--912}
}

OpenURL

Abstract

Work on the semantics of questions has argued that the relation between a question and its answer(s) can be cast in terms of logical entailment. In this paper, we demonstrate how computational systems designed to recognize textual entailment can be used to enhance the accuracy of current open-domain automatic question answering (Q/A) systems. In our experiments, we show that when textual entailment information is used to either filter or rank answers returned by a Q/A system, accuracy can be increased by as much as 20 % overall. 1

Keyphrases

textual entailment open-domain question answering computational system logical entailment textual entailment information rank answer current open-domain automatic question answering

DMCA