Simple Weighting Techniques for Query Expansion in Biomedical Document Retrieval

Young-In SONG; Kyoung-Soo HAN; So-Young PARK; Sang-Bum KIM; Hae-Chang RIM

doi:10.1093/ietisy/e90-d.11.1873

Simple Weighting Techniques for Query Expansion in Biomedical Document Retrieval

Young-In SONG, Kyoung-Soo HAN, So-Young PARK, Sang-Bum KIM, Hae-Chang RIM

Full Text Views

0

Cite this

Summary :

In this paper, we propose two weighting techniques to improve performances of query expansion in biomedical document retrieval, especially when a short biomedical term in a query is expanded with its synonymous multi-word terms. When a query contains synonymous terms of different lengths, a traditional IR model highly ranks a document containing a longer terminology because a longer terminology has more chance to be matched with a query. However, such preference is clearly inappropriate and it often yields an unsatisfactory result. To alleviate the bias weighting problem, we devise a method of normalizing the weights of query terms in a long multi-word biomedical term, and a method of discriminating terms by using inverse terminology frequency which is a novel statistics estimated in a query domain. The experiment results on MEDLINE corpus show that our two simple techniques improve the retrieval performance by adjusting the inadequate preference for long multi-word terminologies in an expanded query.

Publication: IEICE TRANSACTIONS on Information Vol.E90-D No.11 pp.1873-1876

Publication Date: 2007/11/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e90-d.11.1873

Type of Manuscript: LETTER

Category: Contents Technology and Web Information Systems

Cite this

Copy

Young-In SONG, Kyoung-Soo HAN, So-Young PARK, Sang-Bum KIM, Hae-Chang RIM, "Simple Weighting Techniques for Query Expansion in Biomedical Document Retrieval" in IEICE TRANSACTIONS on Information, vol. E90-D, no. 11, pp. 1873-1876, November 2007, doi: 10.1093/ietisy/e90-d.11.1873.
Abstract: In this paper, we propose two weighting techniques to improve performances of query expansion in biomedical document retrieval, especially when a short biomedical term in a query is expanded with its synonymous multi-word terms. When a query contains synonymous terms of different lengths, a traditional IR model highly ranks a document containing a longer terminology because a longer terminology has more chance to be matched with a query. However, such preference is clearly inappropriate and it often yields an unsatisfactory result. To alleviate the bias weighting problem, we devise a method of normalizing the weights of query terms in a long multi-word biomedical term, and a method of discriminating terms by using inverse terminology frequency which is a novel statistics estimated in a query domain. The experiment results on MEDLINE corpus show that our two simple techniques improve the retrieval performance by adjusting the inadequate preference for long multi-word terminologies in an expanded query.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.11.1873/_p

Copy

@ARTICLE{e90-d_11_1873,
author={Young-In SONG, Kyoung-Soo HAN, So-Young PARK, Sang-Bum KIM, Hae-Chang RIM, },
journal={IEICE TRANSACTIONS on Information},
title={Simple Weighting Techniques for Query Expansion in Biomedical Document Retrieval},
year={2007},
volume={E90-D},
number={11},
pages={1873-1876},
abstract={In this paper, we propose two weighting techniques to improve performances of query expansion in biomedical document retrieval, especially when a short biomedical term in a query is expanded with its synonymous multi-word terms. When a query contains synonymous terms of different lengths, a traditional IR model highly ranks a document containing a longer terminology because a longer terminology has more chance to be matched with a query. However, such preference is clearly inappropriate and it often yields an unsatisfactory result. To alleviate the bias weighting problem, we devise a method of normalizing the weights of query terms in a long multi-word biomedical term, and a method of discriminating terms by using inverse terminology frequency which is a novel statistics estimated in a query domain. The experiment results on MEDLINE corpus show that our two simple techniques improve the retrieval performance by adjusting the inadequate preference for long multi-word terminologies in an expanded query.},
keywords={},
doi={10.1093/ietisy/e90-d.11.1873},
ISSN={1745-1361},
month={November},}

Copy

TY - JOUR
TI - Simple Weighting Techniques for Query Expansion in Biomedical Document Retrieval
T2 - IEICE TRANSACTIONS on Information
SP - 1873
EP - 1876
AU - Young-In SONG
AU - Kyoung-Soo HAN
AU - So-Young PARK
AU - Sang-Bum KIM
AU - Hae-Chang RIM
PY - 2007
DO - 10.1093/ietisy/e90-d.11.1873
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2007
AB - In this paper, we propose two weighting techniques to improve performances of query expansion in biomedical document retrieval, especially when a short biomedical term in a query is expanded with its synonymous multi-word terms. When a query contains synonymous terms of different lengths, a traditional IR model highly ranks a document containing a longer terminology because a longer terminology has more chance to be matched with a query. However, such preference is clearly inappropriate and it often yields an unsatisfactory result. To alleviate the bias weighting problem, we devise a method of normalizing the weights of query terms in a long multi-word biomedical term, and a method of discriminating terms by using inverse terminology frequency which is a novel statistics estimated in a query domain. The experiment results on MEDLINE corpus show that our two simple techniques improve the retrieval performance by adjusting the inadequate preference for long multi-word terminologies in an expanded query.
ER -