Concept based document retrieval for genomics literature

Rudolf Berend Trieschnigg; Wessel Kraaij; Martijn Schuemie

Concept based document retrieval for genomics literature

Rudolf Berend Trieschnigg, Wessel Kraaij, Martijn Schuemie

Databases (Former)

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

71 Downloads (Pure)

Abstract

The 2006 TREC Genomics evaluation focuses on document, passage and aspect retrieval in the genomics domain. The Erasmus Medical Center, TNO and University of Twente collaborated on an approach combining concept tagging (named entity recognition) and information retrieval based on language models. Experiments carried out on the 2004 and 2006 collections show that the system based on a concept index could not outperform the baseline system based on words. Further investigation has to show why the index based on concepts performs poor.

Original language	English
Title of host publication	The Fifteenth Text REtrieval Conference (TREC 2006) Proceedings
Editors	E.M Voorhees, L.P. Buckland
Place of Publication	Gaithersburg
Publisher	NIST
Pages	453
Number of pages	8
Publication status	Published - Nov 2006
Event	Fifteenth Text REtrieval Conference, TREC-15 2006 - Gaithersburg, United States Duration: 14 Nov 2006 → 17 Nov 2006 Conference number: 15

Publication series

Name	NIST Special Publication
Publisher	National Institute of Standards and Technology (NIST)
Number	10
Volume	SP 500

Conference

Conference	Fifteenth Text REtrieval Conference, TREC-15 2006
Abbreviated title	TREC
Country/Territory	United States
City	Gaithersburg
Period	14/11/06 → 17/11/06

Keywords

EWI-8274
IR-66653
METIS-237651

Access to Document

http://trec.nist.gov/pubs/trec15/t15_proceedings.html

Cite this

@inproceedings{ba05de14026f423e80a0cbce48d0d6f0,

title = "Concept based document retrieval for genomics literature",

abstract = "The 2006 TREC Genomics evaluation focuses on document, passage and aspect retrieval in the genomics domain. The Erasmus Medical Center, TNO and University of Twente collaborated on an approach combining concept tagging (named entity recognition) and information retrieval based on language models. Experiments carried out on the 2004 and 2006 collections show that the system based on a concept index could not outperform the baseline system based on words. Further investigation has to show why the index based on concepts performs poor.",

keywords = "EWI-8274, IR-66653, METIS-237651",

author = "Trieschnigg, {Rudolf Berend} and Wessel Kraaij and Martijn Schuemie",

year = "2006",

month = nov,

language = "English",

series = "NIST Special Publication",

publisher = "NIST",

number = "10",

pages = "453",

editor = "E.M Voorhees and L.P. Buckland",

booktitle = "The Fifteenth Text REtrieval Conference (TREC 2006) Proceedings",

note = "Fifteenth Text REtrieval Conference, TREC-15 2006, TREC ; Conference date: 14-11-2006 Through 17-11-2006",

}

Trieschnigg, RB, Kraaij, W & Schuemie, M 2006, Concept based document retrieval for genomics literature. in EM Voorhees & LP Buckland (eds), The Fifteenth Text REtrieval Conference (TREC 2006) Proceedings. NIST Special Publication, no. 10, vol. SP 500, NIST, Gaithersburg, pp. 453, Fifteenth Text REtrieval Conference, TREC-15 2006, Gaithersburg, Maryland, United States, 14/11/06. <http://trec.nist.gov/pubs/trec15/t15_proceedings.html>

Concept based document retrieval for genomics literature. / Trieschnigg, Rudolf Berend; Kraaij, Wessel; Schuemie, Martijn.
The Fifteenth Text REtrieval Conference (TREC 2006) Proceedings. ed. / E.M Voorhees; L.P. Buckland. Gaithersburg: NIST, 2006. p. 453 (NIST Special Publication; Vol. SP 500, No. 10).

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

TY - GEN

T1 - Concept based document retrieval for genomics literature

AU - Trieschnigg, Rudolf Berend

AU - Kraaij, Wessel

AU - Schuemie, Martijn

N1 - Conference code: 15

PY - 2006/11

Y1 - 2006/11

N2 - The 2006 TREC Genomics evaluation focuses on document, passage and aspect retrieval in the genomics domain. The Erasmus Medical Center, TNO and University of Twente collaborated on an approach combining concept tagging (named entity recognition) and information retrieval based on language models. Experiments carried out on the 2004 and 2006 collections show that the system based on a concept index could not outperform the baseline system based on words. Further investigation has to show why the index based on concepts performs poor.

AB - The 2006 TREC Genomics evaluation focuses on document, passage and aspect retrieval in the genomics domain. The Erasmus Medical Center, TNO and University of Twente collaborated on an approach combining concept tagging (named entity recognition) and information retrieval based on language models. Experiments carried out on the 2004 and 2006 collections show that the system based on a concept index could not outperform the baseline system based on words. Further investigation has to show why the index based on concepts performs poor.

KW - EWI-8274

KW - IR-66653

KW - METIS-237651

M3 - Conference contribution

T3 - NIST Special Publication

SP - 453

BT - The Fifteenth Text REtrieval Conference (TREC 2006) Proceedings

A2 - Voorhees, E.M

A2 - Buckland, L.P.

PB - NIST

CY - Gaithersburg

T2 - Fifteenth Text REtrieval Conference, TREC-15 2006

Y2 - 14 November 2006 through 17 November 2006

ER -

Concept based document retrieval for genomics literature

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this