Goal detection from natural language queries

Yulan He

doi:10.1007/978-3-642-13881-2_16

Goal detection from natural language queries

Yulan He

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

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.

Original language	English
Title of host publication	Natural language processing and information systems
Subtitle of host publication	15th international conference on applications of natural language to information systems, NLDB 2010, Cardiff, UK, June 23-25, 2010. Proceedings
Editors	Christina J. Hopfe, Yacine Rezgui, Elisabeth Métais, Alun Preece, Haijiang Li
Place of Publication	Berlin (DE)
Publisher	Springer
Pages	157-168
Number of pages	12
Volume	6177
ISBN (Print)	3-642-13880-2, 978-3-642-13880-5
DOIs	https://doi.org/10.1007/978-3-642-13881-2_16
Publication status	Published - 2010
Event	15th international conference on applications of natural language to information systems, NLDB 2010 - Cardiff, United Kingdom Duration: 23 Jun 2010 → 25 Jun 2010

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	6177
ISSN (Print)	0302-9743

Conference

Conference	15th international conference on applications of natural language to information systems, NLDB 2010
Country/Territory	United Kingdom
City	Cardiff
Period	23/06/10 → 25/06/10

Keywords

goal detection
tree-augmented Naive Bayes networks
natural language query

Access to Document

10.1007/978-3-642-13881-2_16

Cite this

He, Y. (2010). Goal detection from natural language queries. In C. J. Hopfe, Y. Rezgui, E. Métais, A. Preece, & H. Li (Eds.), Natural 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 (Vol. 6177, pp. 157-168). (Lecture notes in computer science; Vol. 6177). Springer. https://doi.org/10.1007/978-3-642-13881-2_16

He, Yulan. / Goal detection from natural language queries. Natural 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. editor / Christina J. Hopfe ; Yacine Rezgui ; Elisabeth Métais ; Alun Preece ; Haijiang Li. Vol. 6177 Berlin (DE) : Springer, 2010. pp. 157-168 (Lecture notes in computer science).

@inproceedings{4aca7c6bb9d0481983e2b57d959a5963,

title = "Goal detection from natural language queries",

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.",

keywords = "goal detection, tree-augmented Naive Bayes networks, natural language query",

author = "Yulan He",

year = "2010",

doi = "10.1007/978-3-642-13881-2_16",

language = "English",

isbn = "3-642-13880-2",

volume = "6177",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "157--168",

editor = "Hopfe, {Christina J.} and Yacine Rezgui and Elisabeth M{\'e}tais and Alun Preece and Haijiang Li",

booktitle = "Natural language processing and information systems",

address = "Germany",

note = "15th international conference on applications of natural language to information systems, NLDB 2010 ; Conference date: 23-06-2010 Through 25-06-2010",

}

He, Y 2010, Goal detection from natural language queries. in CJ Hopfe, Y Rezgui, E Métais, A Preece & H Li (eds), Natural 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. vol. 6177, Lecture notes in computer science, vol. 6177, Springer, Berlin (DE), pp. 157-168, 15th international conference on applications of natural language to information systems, NLDB 2010, Cardiff, United Kingdom, 23/06/10. https://doi.org/10.1007/978-3-642-13881-2_16

Goal detection from natural language queries. / He, Yulan.
Natural 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. ed. / Christina J. Hopfe; Yacine Rezgui; Elisabeth Métais; Alun Preece; Haijiang Li. Vol. 6177 Berlin (DE): Springer, 2010. p. 157-168 (Lecture notes in computer science; Vol. 6177).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Goal detection from natural language queries

AU - He, Yulan

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

KW - goal detection

KW - tree-augmented Naive Bayes networks

KW - natural language query

UR - http://www.scopus.com/inward/record.url?scp=77955442161&partnerID=8YFLogxK

UR - http://www.springerlink.com/content/262m1j6m1489210q/

U2 - 10.1007/978-3-642-13881-2_16

DO - 10.1007/978-3-642-13881-2_16

M3 - Conference publication

AN - SCOPUS:77955442161

SN - 3-642-13880-2

SN - 978-3-642-13880-5

VL - 6177

T3 - Lecture notes in computer science

SP - 157

EP - 168

BT - Natural language processing and information systems

A2 - Hopfe, Christina J.

A2 - Rezgui, Yacine

A2 - Métais, Elisabeth

A2 - Preece, Alun

A2 - Li, Haijiang

PB - Springer

CY - Berlin (DE)

T2 - 15th international conference on applications of natural language to information systems, NLDB 2010

Y2 - 23 June 2010 through 25 June 2010

ER -

He Y. Goal detection from natural language queries. In Hopfe CJ, Rezgui Y, Métais E, Preece A, Li H, editors, Natural 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. Vol. 6177. Berlin (DE): Springer. 2010. p. 157-168. (Lecture notes in computer science). doi: 10.1007/978-3-642-13881-2_16

Goal detection from natural language queries

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this