Using Parsimonious Language Models on Web Data

Rianne Kaptein; Rongmei Li; Djoerd Hiemstra; Jaap Kamps

doi:10.1145/1390334.1390491

Using Parsimonious Language Models on Web Data

Rianne Kaptein, Rongmei Li, Djoerd Hiemstra, Jaap Kamps

Databases (Former)

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

5 Downloads (Pure)

Abstract

In this paper we explore the use of parsimonious language models for web retrieval. These models are smaller thus more efficient than the standard language models and are therefore well suited for large-scale web retrieval. We have conducted experiments on four TREC topic sets, and found that the parsimonious language model results in improvement of retrieval effectiveness over the standard language model for all data-sets and measures. In all cases the improvement is significant, and more substantial than in earlier experiments on newspaper/newswire data.

Original language	English
Title of host publication	SIGIR '08
Subtitle of host publication	Proceedings of the 31th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
Editors	Tat-Seng Chua, Mun-Kew Leong
Place of Publication	New York NY, USA
Publisher	ACM Press
Pages	763-764
Number of pages	2
ISBN (Print)	978-1-60558-164-4
DOIs	https://doi.org/10.1145/1390334.1390491
Publication status	Published - 20 Jul 2008
Event	31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008 - Singapore, Singapore Duration: 20 Jul 2008 → 25 Jul 2008 Conference number: 31

Conference

Conference	31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008
Abbreviated title	SIGIR
Country/Territory	Singapore
City	Singapore
Period	20/07/08 → 25/07/08

Keywords

DB-IR: INFORMATION RETRIEVAL
IR-64723
METIS-250954
EWI-12282

Access to Document

10.1145/1390334.1390491

Cite this

@inproceedings{e43e33f2029b4691aff8325fcc1a69ad,

title = "Using Parsimonious Language Models on Web Data",

abstract = "In this paper we explore the use of parsimonious language models for web retrieval. These models are smaller thus more efficient than the standard language models and are therefore well suited for large-scale web retrieval. We have conducted experiments on four TREC topic sets, and found that the parsimonious language model results in improvement of retrieval effectiveness over the standard language model for all data-sets and measures. In all cases the improvement is significant, and more substantial than in earlier experiments on newspaper/newswire data.",

keywords = "DB-IR: INFORMATION RETRIEVAL, IR-64723, METIS-250954, EWI-12282",

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

year = "2008",

month = jul,

day = "20",

doi = "10.1145/1390334.1390491",

language = "English",

isbn = "978-1-60558-164-4",

pages = "763--764",

editor = "Tat-Seng Chua and Mun-Kew Leong",

booktitle = "SIGIR '08",

publisher = "ACM Press",

note = "31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, SIGIR ; Conference date: 20-07-2008 Through 25-07-2008",

}

Kaptein, R, Li, R, Hiemstra, D & Kamps, J 2008, Using Parsimonious Language Models on Web Data. in T-S Chua & M-K Leong (eds), SIGIR '08: Proceedings of the 31th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York NY, USA, pp. 763-764, 31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, Singapore, Singapore, 20/07/08. https://doi.org/10.1145/1390334.1390491

Using Parsimonious Language Models on Web Data. / Kaptein, Rianne; Li, Rongmei; Hiemstra, Djoerd et al.

SIGIR '08: Proceedings of the 31th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ed. / Tat-Seng Chua; Mun-Kew Leong. New York NY, USA : ACM Press, 2008. p. 763-764.

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

TY - GEN

T1 - Using Parsimonious Language Models on Web Data

AU - Kaptein, Rianne

AU - Li, Rongmei

AU - Hiemstra, Djoerd

AU - Kamps, Jaap

N1 - Conference code: 31

PY - 2008/7/20

Y1 - 2008/7/20

N2 - In this paper we explore the use of parsimonious language models for web retrieval. These models are smaller thus more efficient than the standard language models and are therefore well suited for large-scale web retrieval. We have conducted experiments on four TREC topic sets, and found that the parsimonious language model results in improvement of retrieval effectiveness over the standard language model for all data-sets and measures. In all cases the improvement is significant, and more substantial than in earlier experiments on newspaper/newswire data.

AB - In this paper we explore the use of parsimonious language models for web retrieval. These models are smaller thus more efficient than the standard language models and are therefore well suited for large-scale web retrieval. We have conducted experiments on four TREC topic sets, and found that the parsimonious language model results in improvement of retrieval effectiveness over the standard language model for all data-sets and measures. In all cases the improvement is significant, and more substantial than in earlier experiments on newspaper/newswire data.

KW - DB-IR: INFORMATION RETRIEVAL

KW - IR-64723

KW - METIS-250954

KW - EWI-12282

U2 - 10.1145/1390334.1390491

DO - 10.1145/1390334.1390491

M3 - Conference contribution

SN - 978-1-60558-164-4

SP - 763

EP - 764

BT - SIGIR '08

A2 - Chua, Tat-Seng

A2 - Leong, Mun-Kew

PB - ACM Press

CY - New York NY, USA

T2 - 31st Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008

Y2 - 20 July 2008 through 25 July 2008

ER -

Using Parsimonious Language Models on Web Data

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this