A Cross-lingual Framework for Monolingual Biomedical Information Retrieval

Rudolf Berend Trieschnigg; Djoerd Hiemstra; Franciska M.G. de Jong; Wessel Kraaij

doi:10.1145/1871437.1871463

A Cross-lingual Framework for Monolingual Biomedical Information Retrieval

Rudolf Berend Trieschnigg
, Djoerd Hiemstra
, Franciska M.G. de Jong
, Wessel Kraaij

Databases (Former)

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

17 Citations (Scopus)

92 Downloads (Pure)

Abstract

An important challenge for biomedical information retrieval (IR) is dealing with the complex, inconsistent and ambiguous biomedical terminology. Frequently, a concept-based representation defined in terms of a domain-specific terminological resource is employed to deal with this challenge. In this paper, we approach the incorporation of a concept-based representation in monolingual biomedical IR from a cross-lingual perspective. In the proposed framework, this is reali sed by translating and matching between text and concept-based representations. The approach allows for deployment of a rich set of techniques proposed and evaluated in traditional cross-lingual IR. We compare six translation models and measure their effectiveness in the biomedical domain. We demonstrate that the approach can result in significant improvements in retrieval effectiveness over word-based retrieval. Moreover, we demonstrate increased effectiveness of a CLIR framework for monolingual biomedical IR if basic translations models are combined.

Original language	Undefined
Title of host publication	Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10)
Editors	J. Huang, N. Koudas, G. Jones, Xindong Wu, K. Collins-Thompson, Aijun An
Place of Publication	New York
Publisher	Association for Computing Machinery
Pages	169-178
Number of pages	10
ISBN (Print)	978-1-4503-0099-5
DOIs	https://doi.org/10.1145/1871437.1871463
Publication status	Published - 2010
Event	19th ACM International Conference on Information and Knowledge Management, CIKM 2010 - Toronto, Canada Duration: 26 Oct 2010 → 30 Oct 2010 Conference number: 19

Publication series

Name
Publisher	ACM

Conference

Conference	19th ACM International Conference on Information and Knowledge Management, CIKM 2010
Abbreviated title	CIKM
Country/Territory	Canada
City	Toronto
Period	26/10/10 → 30/10/10

Keywords

IR-72470
METIS-270940
Biomedical information retrieval
CR-H.3.3
Language modeling
TREC Genomics
EWI-18213
CLIR framework

Access to Document

10.1145/1871437.1871463

CIKM.2010.trieschnigg

http://doi.acm.org/10.1145/1871437.1871463

Cite this

Trieschnigg, R. B., Hiemstra, D., de Jong, F. M. G., & Kraaij, W. (2010). A Cross-lingual Framework for Monolingual Biomedical Information Retrieval. In J. Huang, N. Koudas, G. Jones, X. Wu, K. Collins-Thompson, & A. An (Eds.), Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10) (pp. 169-178). Association for Computing Machinery. https://doi.org/10.1145/1871437.1871463

Trieschnigg, Rudolf Berend ; Hiemstra, Djoerd ; de Jong, Franciska M.G. et al. / A Cross-lingual Framework for Monolingual Biomedical Information Retrieval. Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10). editor / J. Huang ; N. Koudas ; G. Jones ; Xindong Wu ; K. Collins-Thompson ; Aijun An. New York : Association for Computing Machinery, 2010. pp. 169-178

@inproceedings{840a17450ad5498da3e42c7995c3aaf9,

title = "A Cross-lingual Framework for Monolingual Biomedical Information Retrieval",

abstract = "An important challenge for biomedical information retrieval (IR) is dealing with the complex, inconsistent and ambiguous biomedical terminology. Frequently, a concept-based representation defined in terms of a domain-specific terminological resource is employed to deal with this challenge. In this paper, we approach the incorporation of a concept-based representation in monolingual biomedical IR from a cross-lingual perspective. In the proposed framework, this is reali sed by translating and matching between text and concept-based representations. The approach allows for deployment of a rich set of techniques proposed and evaluated in traditional cross-lingual IR. We compare six translation models and measure their effectiveness in the biomedical domain. We demonstrate that the approach can result in significant improvements in retrieval effectiveness over word-based retrieval. Moreover, we demonstrate increased effectiveness of a CLIR framework for monolingual biomedical IR if basic translations models are combined.",

keywords = "IR-72470, METIS-270940, Biomedical information retrieval, CR-H.3.3, Language modeling, TREC Genomics, EWI-18213, CLIR framework",

author = "Trieschnigg, \{Rudolf Berend\} and Djoerd Hiemstra and \{de Jong\}, \{Franciska M.G.\} and Wessel Kraaij",

note = "accepted for publication ; 19th ACM International Conference on Information and Knowledge Management, CIKM 2010 ; Conference date: 26-10-2010 Through 30-10-2010",

year = "2010",

doi = "10.1145/1871437.1871463",

language = "Undefined",

isbn = "978-1-4503-0099-5",

publisher = "Association for Computing Machinery",

pages = "169--178",

editor = "J. Huang and N. Koudas and G. Jones and Xindong Wu and K. Collins-Thompson and Aijun An",

booktitle = "Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10)",

address = "United States",

}

Trieschnigg, RB, Hiemstra, D, de Jong, FMG & Kraaij, W 2010, A Cross-lingual Framework for Monolingual Biomedical Information Retrieval. in J Huang, N Koudas, G Jones, X Wu, K Collins-Thompson & A An (eds), Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10). Association for Computing Machinery, New York, pp. 169-178, 19th ACM International Conference on Information and Knowledge Management, CIKM 2010, Toronto, Ontario, Canada, 26/10/10. https://doi.org/10.1145/1871437.1871463

A Cross-lingual Framework for Monolingual Biomedical Information Retrieval. / Trieschnigg, Rudolf Berend; Hiemstra, Djoerd; de Jong, Franciska M.G. et al.
Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10). ed. / J. Huang; N. Koudas; G. Jones; Xindong Wu; K. Collins-Thompson; Aijun An. New York: Association for Computing Machinery, 2010. p. 169-178.

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

TY - GEN

T1 - A Cross-lingual Framework for Monolingual Biomedical Information Retrieval

AU - Trieschnigg, Rudolf Berend

AU - Hiemstra, Djoerd

AU - de Jong, Franciska M.G.

AU - Kraaij, Wessel

N1 - Conference code: 19

PY - 2010

Y1 - 2010

N2 - An important challenge for biomedical information retrieval (IR) is dealing with the complex, inconsistent and ambiguous biomedical terminology. Frequently, a concept-based representation defined in terms of a domain-specific terminological resource is employed to deal with this challenge. In this paper, we approach the incorporation of a concept-based representation in monolingual biomedical IR from a cross-lingual perspective. In the proposed framework, this is reali sed by translating and matching between text and concept-based representations. The approach allows for deployment of a rich set of techniques proposed and evaluated in traditional cross-lingual IR. We compare six translation models and measure their effectiveness in the biomedical domain. We demonstrate that the approach can result in significant improvements in retrieval effectiveness over word-based retrieval. Moreover, we demonstrate increased effectiveness of a CLIR framework for monolingual biomedical IR if basic translations models are combined.

AB - An important challenge for biomedical information retrieval (IR) is dealing with the complex, inconsistent and ambiguous biomedical terminology. Frequently, a concept-based representation defined in terms of a domain-specific terminological resource is employed to deal with this challenge. In this paper, we approach the incorporation of a concept-based representation in monolingual biomedical IR from a cross-lingual perspective. In the proposed framework, this is reali sed by translating and matching between text and concept-based representations. The approach allows for deployment of a rich set of techniques proposed and evaluated in traditional cross-lingual IR. We compare six translation models and measure their effectiveness in the biomedical domain. We demonstrate that the approach can result in significant improvements in retrieval effectiveness over word-based retrieval. Moreover, we demonstrate increased effectiveness of a CLIR framework for monolingual biomedical IR if basic translations models are combined.

KW - IR-72470

KW - METIS-270940

KW - Biomedical information retrieval

KW - CR-H.3.3

KW - Language modeling

KW - TREC Genomics

KW - EWI-18213

KW - CLIR framework

U2 - 10.1145/1871437.1871463

DO - 10.1145/1871437.1871463

M3 - Conference contribution

SN - 978-1-4503-0099-5

SP - 169

EP - 178

BT - Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10)

A2 - Huang, J.

A2 - Koudas, N.

A2 - Jones, G.

A2 - Wu, Xindong

A2 - Collins-Thompson, K.

A2 - An, Aijun

PB - Association for Computing Machinery

CY - New York

T2 - 19th ACM International Conference on Information and Knowledge Management, CIKM 2010

Y2 - 26 October 2010 through 30 October 2010

ER -

Trieschnigg RB, Hiemstra D, de Jong FMG, Kraaij W. A Cross-lingual Framework for Monolingual Biomedical Information Retrieval. In Huang J, Koudas N, Jones G, Wu X, Collins-Thompson K, An A, editors, Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM '10). New York: Association for Computing Machinery. 2010. p. 169-178 doi: 10.1145/1871437.1871463