Entity Ranking on Graphs: Studies on Expert Finding

H. Rode, Pavel Serdyukov, Djoerd Hiemstra, H. Zaragoza

Research output: Book/ReportReportProfessional

47 Downloads (Pure)

Abstract

Todays web search engines try to offer services for finding various information in addition to simple web pages, like showing locations or answering simple fact queries. Understanding the association of named entities and documents is one of the key steps towards such semantic search tasks. This paper addresses the ranking of entities and models it in a graph-based relevance propagation framework. In particular we study the problem of expert finding as an example of an entity ranking task. Entity containment graphs are introduced that represent the relationship between text fragments on the one hand and their contained entities on the other hand. The paper shows how these graphs can be used to propagate relevance information from the pre-ranked text fragments to their entities. We use this propagation framework to model existing approaches to expert finding based on the entity's indegree and extend them by recursive relevance propagation based on a probabilistic random walk over the entity containment graphs. Experiments on the TREC expert search task compare the retrieval performance of the different graph and propagation models.
Original languageUndefined
Place of PublicationEnschede
PublisherCentre for Telematics and Information Technology (CTIT)
Number of pages8
Publication statusPublished - 26 Nov 2007

Publication series

NameCTIT Technical Report Series
PublisherCentre for Telematics and Information Technology, University of Twente
No.FS-07-05/TR-CTIT-07-81
ISSN (Print)1381-3625

Keywords

  • EWI-11412
  • METIS-245781
  • IR-64466

Cite this

Rode, H., Serdyukov, P., Hiemstra, D., & Zaragoza, H. (2007). Entity Ranking on Graphs: Studies on Expert Finding. (CTIT Technical Report Series; No. FS-07-05/TR-CTIT-07-81). Enschede: Centre for Telematics and Information Technology (CTIT).
Rode, H. ; Serdyukov, Pavel ; Hiemstra, Djoerd ; Zaragoza, H. / Entity Ranking on Graphs: Studies on Expert Finding. Enschede : Centre for Telematics and Information Technology (CTIT), 2007. 8 p. (CTIT Technical Report Series; FS-07-05/TR-CTIT-07-81).
@book{0545a73dd4494694a3dfb2938bb6008a,
title = "Entity Ranking on Graphs: Studies on Expert Finding",
abstract = "Todays web search engines try to offer services for finding various information in addition to simple web pages, like showing locations or answering simple fact queries. Understanding the association of named entities and documents is one of the key steps towards such semantic search tasks. This paper addresses the ranking of entities and models it in a graph-based relevance propagation framework. In particular we study the problem of expert finding as an example of an entity ranking task. Entity containment graphs are introduced that represent the relationship between text fragments on the one hand and their contained entities on the other hand. The paper shows how these graphs can be used to propagate relevance information from the pre-ranked text fragments to their entities. We use this propagation framework to model existing approaches to expert finding based on the entity's indegree and extend them by recursive relevance propagation based on a probabilistic random walk over the entity containment graphs. Experiments on the TREC expert search task compare the retrieval performance of the different graph and propagation models.",
keywords = "EWI-11412, METIS-245781, IR-64466",
author = "H. Rode and Pavel Serdyukov and Djoerd Hiemstra and H. Zaragoza",
year = "2007",
month = "11",
day = "26",
language = "Undefined",
series = "CTIT Technical Report Series",
publisher = "Centre for Telematics and Information Technology (CTIT)",
number = "FS-07-05/TR-CTIT-07-81",
address = "Netherlands",

}

Rode, H, Serdyukov, P, Hiemstra, D & Zaragoza, H 2007, Entity Ranking on Graphs: Studies on Expert Finding. CTIT Technical Report Series, no. FS-07-05/TR-CTIT-07-81, Centre for Telematics and Information Technology (CTIT), Enschede.

Entity Ranking on Graphs: Studies on Expert Finding. / Rode, H.; Serdyukov, Pavel; Hiemstra, Djoerd; Zaragoza, H.

Enschede : Centre for Telematics and Information Technology (CTIT), 2007. 8 p. (CTIT Technical Report Series; No. FS-07-05/TR-CTIT-07-81).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - Entity Ranking on Graphs: Studies on Expert Finding

AU - Rode, H.

AU - Serdyukov, Pavel

AU - Hiemstra, Djoerd

AU - Zaragoza, H.

PY - 2007/11/26

Y1 - 2007/11/26

N2 - Todays web search engines try to offer services for finding various information in addition to simple web pages, like showing locations or answering simple fact queries. Understanding the association of named entities and documents is one of the key steps towards such semantic search tasks. This paper addresses the ranking of entities and models it in a graph-based relevance propagation framework. In particular we study the problem of expert finding as an example of an entity ranking task. Entity containment graphs are introduced that represent the relationship between text fragments on the one hand and their contained entities on the other hand. The paper shows how these graphs can be used to propagate relevance information from the pre-ranked text fragments to their entities. We use this propagation framework to model existing approaches to expert finding based on the entity's indegree and extend them by recursive relevance propagation based on a probabilistic random walk over the entity containment graphs. Experiments on the TREC expert search task compare the retrieval performance of the different graph and propagation models.

AB - Todays web search engines try to offer services for finding various information in addition to simple web pages, like showing locations or answering simple fact queries. Understanding the association of named entities and documents is one of the key steps towards such semantic search tasks. This paper addresses the ranking of entities and models it in a graph-based relevance propagation framework. In particular we study the problem of expert finding as an example of an entity ranking task. Entity containment graphs are introduced that represent the relationship between text fragments on the one hand and their contained entities on the other hand. The paper shows how these graphs can be used to propagate relevance information from the pre-ranked text fragments to their entities. We use this propagation framework to model existing approaches to expert finding based on the entity's indegree and extend them by recursive relevance propagation based on a probabilistic random walk over the entity containment graphs. Experiments on the TREC expert search task compare the retrieval performance of the different graph and propagation models.

KW - EWI-11412

KW - METIS-245781

KW - IR-64466

M3 - Report

T3 - CTIT Technical Report Series

BT - Entity Ranking on Graphs: Studies on Expert Finding

PB - Centre for Telematics and Information Technology (CTIT)

CY - Enschede

ER -

Rode H, Serdyukov P, Hiemstra D, Zaragoza H. Entity Ranking on Graphs: Studies on Expert Finding. Enschede: Centre for Telematics and Information Technology (CTIT), 2007. 8 p. (CTIT Technical Report Series; FS-07-05/TR-CTIT-07-81).