A language modeling framework for expert finding

Krisztian Balog, Leif Azzopardi, Maarten de Rijke

Research output: Contribution to journalArticle

146 Citations (Scopus)

Abstract

Statistical language models have been successfully applied to many information retrieval tasks, including expert finding: the process of identifying experts given a particular topic. In this paper, we introduce and detail language modeling approaches that integrate the representation, association and search of experts using various textual data sources into a generative probabilistic framework. This provides a simple, intuitive, and extensible theoretical framework to underpin research into expertise search. To demonstrate the flexibility of the framework, two search strategies to find experts are modeled that incorporate different types of evidence extracted from the data, before being extended to also incorporate co-occurrence information. The models proposed are evaluated in the context of enterprise search systems within an intranet environment, where it is reasonable to assume that the list of experts is known, and that data to be mined is publicly accessible. Our experiments show that excellent performance can be achieved by using these models in such environments, and that this theoretical and empirical work paves the way for future principled extensions.
LanguageEnglish
Pages1-19
Number of pages19
JournalInformation Processing and Management
Volume45
Issue number1
DOIs
Publication statusPublished - 1 Jan 2009
Externally publishedYes

Fingerprint

expert
language
Intranets
Information retrieval
Intranet
information retrieval
expertise
flexibility
Expert finding
Language modeling
Industry
Experiments
experiment
performance
evidence
Expertise
Search strategy
Data sources
Experiment
Language model

Keywords

  • expert finding
  • language modeling
  • intranet search
  • expertise search

Cite this

Balog, Krisztian ; Azzopardi, Leif ; de Rijke, Maarten. / A language modeling framework for expert finding. In: Information Processing and Management. 2009 ; Vol. 45, No. 1. pp. 1-19.
@article{7da5bcf9c6a94d159645bb07aada4de2,
title = "A language modeling framework for expert finding",
abstract = "Statistical language models have been successfully applied to many information retrieval tasks, including expert finding: the process of identifying experts given a particular topic. In this paper, we introduce and detail language modeling approaches that integrate the representation, association and search of experts using various textual data sources into a generative probabilistic framework. This provides a simple, intuitive, and extensible theoretical framework to underpin research into expertise search. To demonstrate the flexibility of the framework, two search strategies to find experts are modeled that incorporate different types of evidence extracted from the data, before being extended to also incorporate co-occurrence information. The models proposed are evaluated in the context of enterprise search systems within an intranet environment, where it is reasonable to assume that the list of experts is known, and that data to be mined is publicly accessible. Our experiments show that excellent performance can be achieved by using these models in such environments, and that this theoretical and empirical work paves the way for future principled extensions.",
keywords = "expert finding, language modeling, intranet search, expertise search",
author = "Krisztian Balog and Leif Azzopardi and {de Rijke}, Maarten",
year = "2009",
month = "1",
day = "1",
doi = "10.1016/j.ipm.2008.06.003",
language = "English",
volume = "45",
pages = "1--19",
journal = "Information Processing and Management",
issn = "0306-4573",
number = "1",

}

A language modeling framework for expert finding. / Balog, Krisztian; Azzopardi, Leif; de Rijke, Maarten.

In: Information Processing and Management, Vol. 45, No. 1, 01.01.2009, p. 1-19.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A language modeling framework for expert finding

AU - Balog, Krisztian

AU - Azzopardi, Leif

AU - de Rijke, Maarten

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Statistical language models have been successfully applied to many information retrieval tasks, including expert finding: the process of identifying experts given a particular topic. In this paper, we introduce and detail language modeling approaches that integrate the representation, association and search of experts using various textual data sources into a generative probabilistic framework. This provides a simple, intuitive, and extensible theoretical framework to underpin research into expertise search. To demonstrate the flexibility of the framework, two search strategies to find experts are modeled that incorporate different types of evidence extracted from the data, before being extended to also incorporate co-occurrence information. The models proposed are evaluated in the context of enterprise search systems within an intranet environment, where it is reasonable to assume that the list of experts is known, and that data to be mined is publicly accessible. Our experiments show that excellent performance can be achieved by using these models in such environments, and that this theoretical and empirical work paves the way for future principled extensions.

AB - Statistical language models have been successfully applied to many information retrieval tasks, including expert finding: the process of identifying experts given a particular topic. In this paper, we introduce and detail language modeling approaches that integrate the representation, association and search of experts using various textual data sources into a generative probabilistic framework. This provides a simple, intuitive, and extensible theoretical framework to underpin research into expertise search. To demonstrate the flexibility of the framework, two search strategies to find experts are modeled that incorporate different types of evidence extracted from the data, before being extended to also incorporate co-occurrence information. The models proposed are evaluated in the context of enterprise search systems within an intranet environment, where it is reasonable to assume that the list of experts is known, and that data to be mined is publicly accessible. Our experiments show that excellent performance can be achieved by using these models in such environments, and that this theoretical and empirical work paves the way for future principled extensions.

KW - expert finding

KW - language modeling

KW - intranet search

KW - expertise search

UR - http://www.sciencedirect.com/science/article/pii/S0306457308000678

U2 - 10.1016/j.ipm.2008.06.003

DO - 10.1016/j.ipm.2008.06.003

M3 - Article

VL - 45

SP - 1

EP - 19

JO - Information Processing and Management

T2 - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 1

ER -