Exploring Topic-based Language Models for Effective Web Information Retrieval

Rongmei Li; Rianne Kaptein; Djoerd Hiemstra; Jaap Kamps

Exploring Topic-based Language Models for Effective Web Information Retrieval

Rongmei Li, Rianne Kaptein, Djoerd Hiemstra, Jaap Kamps

Databases (Former)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

13 Downloads (Pure)

Abstract

The main obstacle for providing focused search is the relative opaqueness of search request -- searchers tend to express their complex information needs in only a couple of keywords. Our overall aim is to find out if, and how, topic-based language models can lead to more effective web information retrieval. In this paper we explore retrieval performance of a topic-based model that combines topical models with other language models based on cross-entropy. We first define our topical categories and train our topical models on the .GOV2 corpus by building parsimonious language models. We then test the topic-based model on TREC8 small Web data collection for ad-hoc search.Our experimental results show that the topic-based model outperforms the standard language model and parsimonious model.

Original language	English
Title of host publication	Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2008)
Editors	E. Hoenkamp, M. De Cock, V. Hoste
Place of Publication	Enschede
Publisher	Neslia Paniculata
Pages	65-71
Number of pages	7
ISBN (Print)	978-90-5681-282-9
Publication status	Published - 14 Apr 2008
Event	8th Dutch-Belgian Information Retrieval Workshop, DIR 2008 - Maastricht, Netherlands Duration: 14 Apr 2008 → 15 Apr 2008 Conference number: 8

Conference

Conference	8th Dutch-Belgian Information Retrieval Workshop, DIR 2008
Abbreviated title	DIR
Country	Netherlands
City	Maastricht
Period	14/04/08 → 15/04/08

Keywords

DB-IR: INFORMATION RETRIEVAL
IR-64722
METIS-250952
EWI-12277

Access to Document

Rongmei2008exploring
open
Final published version, 167 KB

http://www.ltci.ugent.be/DIR2008/

Fingerprint Dive into the research topics of 'Exploring Topic-based Language Models for Effective Web Information Retrieval'. Together they form a unique fingerprint.

Cite this

@inproceedings{e6899983b667429db92f0bd0d17f58da,

title = "Exploring Topic-based Language Models for Effective Web Information Retrieval",

abstract = "The main obstacle for providing focused search is the relative opaqueness of search request -- searchers tend to express their complex information needs in only a couple of keywords. Our overall aim is to find out if, and how, topic-based language models can lead to more effective web information retrieval. In this paper we explore retrieval performance of a topic-based model that combines topical models with other language models based on cross-entropy. We first define our topical categories and train our topical models on the .GOV2 corpus by building parsimonious language models. We then test the topic-based model on TREC8 small Web data collection for ad-hoc search.Our experimental results show that the topic-based model outperforms the standard language model and parsimonious model.",

keywords = "DB-IR: INFORMATION RETRIEVAL, IR-64722, METIS-250952, EWI-12277",

author = "Rongmei Li and Rianne Kaptein and Djoerd Hiemstra and Jaap Kamps",

year = "2008",

month = apr,

day = "14",

language = "English",

isbn = "978-90-5681-282-9",

pages = "65--71",

editor = "E. Hoenkamp and {De Cock}, M. and V. Hoste",

booktitle = "Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2008)",

publisher = "Neslia Paniculata",

note = "8th Dutch-Belgian Information Retrieval Workshop, DIR 2008, DIR ; Conference date: 14-04-2008 Through 15-04-2008",

}

Li, R, Kaptein, R, Hiemstra, D & Kamps, J 2008, Exploring Topic-based Language Models for Effective Web Information Retrieval. in E Hoenkamp, M De Cock & V Hoste (eds), Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2008). Neslia Paniculata, Enschede, pp. 65-71, 8th Dutch-Belgian Information Retrieval Workshop, DIR 2008, Maastricht, Netherlands, 14/04/08. <http://www.ltci.ugent.be/DIR2008/>

Exploring Topic-based Language Models for Effective Web Information Retrieval. / Li, Rongmei; Kaptein, Rianne; Hiemstra, Djoerd; Kamps, Jaap.

Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2008). ed. / E. Hoenkamp; M. De Cock; V. Hoste. Enschede : Neslia Paniculata, 2008. p. 65-71.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Exploring Topic-based Language Models for Effective Web Information Retrieval

AU - Li, Rongmei

AU - Kaptein, Rianne

AU - Hiemstra, Djoerd

AU - Kamps, Jaap

N1 - Conference code: 8

PY - 2008/4/14

Y1 - 2008/4/14

N2 - The main obstacle for providing focused search is the relative opaqueness of search request -- searchers tend to express their complex information needs in only a couple of keywords. Our overall aim is to find out if, and how, topic-based language models can lead to more effective web information retrieval. In this paper we explore retrieval performance of a topic-based model that combines topical models with other language models based on cross-entropy. We first define our topical categories and train our topical models on the .GOV2 corpus by building parsimonious language models. We then test the topic-based model on TREC8 small Web data collection for ad-hoc search.Our experimental results show that the topic-based model outperforms the standard language model and parsimonious model.

AB - The main obstacle for providing focused search is the relative opaqueness of search request -- searchers tend to express their complex information needs in only a couple of keywords. Our overall aim is to find out if, and how, topic-based language models can lead to more effective web information retrieval. In this paper we explore retrieval performance of a topic-based model that combines topical models with other language models based on cross-entropy. We first define our topical categories and train our topical models on the .GOV2 corpus by building parsimonious language models. We then test the topic-based model on TREC8 small Web data collection for ad-hoc search.Our experimental results show that the topic-based model outperforms the standard language model and parsimonious model.

KW - DB-IR: INFORMATION RETRIEVAL

KW - IR-64722

KW - METIS-250952

KW - EWI-12277

M3 - Conference contribution

SN - 978-90-5681-282-9

SP - 65

EP - 71

BT - Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2008)

A2 - Hoenkamp, E.

A2 - De Cock, M.

A2 - Hoste, V.

PB - Neslia Paniculata

CY - Enschede

T2 - 8th Dutch-Belgian Information Retrieval Workshop, DIR 2008

Y2 - 14 April 2008 through 15 April 2008

ER -