Goal detection from natural language queries

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations Save citation

Authors

Research units

Abstract

This paper aims to identify the communication goal(s) of a user's information-seeking query out of a finite set of within-domain goals in natural language queries. It proposes using Tree-Augmented Naive Bayes networks (TANs) for goal detection. The problem is formulated as N binary decisions, and each is performed by a TAN. Comparative study has been carried out to compare the performance with Naive Bayes, fully-connected TANs, and multi-layer neural networks. Experimental results show that TANs consistently give better results when tested on the ATIS and DARPA Communicator corpora.

Request a copy

Request a copy

Details

Publication date2010
Publication titleNatural language processing and information systems : 15th international conference on applications of natural language to information systems, NLDB 2010, Cardiff, UK, June 23-25, 2010. Proceedings
EditorsChristina J. Hopfe, Yacine Rezgui, Elisabeth Métais, Alun Preece, Haijiang Li
Place of PublicationBerlin (DE)
PublisherSpringer
Pages157-168
Number of pages12
Volume6177
ISBN (Print)3-642-13880-2, 978-3-642-13880-5
Original languageEnglish
Event15th international conference on applications of natural language to information systems, NLDB 2010 - Cardiff, United Kingdom

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume6177
ISSN (Print)0302-9743

Conference

Conference15th international conference on applications of natural language to information systems, NLDB 2010
CountryUnited Kingdom
CityCardiff
Period23/06/1025/06/10

    Keywords

  • goal detection, tree-augmented Naive Bayes networks, natural language query

DOI

Employable Graduates; Exploitable Research

Copy the text from this field...