@inproceedings{wang-etal-2012-biomedical,
title = "Biomedical {C}hinese-{E}nglish {CLIR} Using an Extended {CM}e{SH} Resource to Expand Queries",
author = "Wang, Xinkai and
Thompson, Paul and
Tsujii, Jun{'}ichi and
Ananiadou, Sophia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/316_Paper.pdf",
pages = "1148--1155",
abstract = "Cross-lingual information retrieval (CLIR) involving the Chinese language has been thoroughly studied in the general language domain, but rarely in the biomedical domain, due to the lack of suitable linguistic resources and parsing tools. In this paper, we describe a Chinese-English CLIR system for biomedical literature, which exploits a bilingual ontology, the ``eCMeSH Tree''''''''. This is an extension of the Chinese Medical Subject Headings (CMeSH) Tree, based on Medical Subject Headings (MeSH). Using the 2006 and 2007 TREC Genomics track data, we have evaluated the performance of the eCMeSH Tree in expanding queries. We have compared our results to those obtained using two other approaches, i.e. pseudo-relevance feedback (PRF) and document translation (DT). Subsequently, we evaluate the performance of different combinations of these three retrieval methods. Our results show that our method of expanding queries using the eCMeSH Tree can outperform the PRF method. Furthermore, combining this method with PRF and DT helps to smooth the differences in query expansion, and consequently results in the best performance amongst all experiments reported. All experiments compare the use of two different retrieval models, i.e. Okapi BM25 and a query likelihood language model. In general, the former performs slightly better.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2012-biomedical">
<titleInfo>
<title>Biomedical Chinese-English CLIR Using an Extended CMeSH Resource to Expand Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinkai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual information retrieval (CLIR) involving the Chinese language has been thoroughly studied in the general language domain, but rarely in the biomedical domain, due to the lack of suitable linguistic resources and parsing tools. In this paper, we describe a Chinese-English CLIR system for biomedical literature, which exploits a bilingual ontology, the “eCMeSH Tree””””. This is an extension of the Chinese Medical Subject Headings (CMeSH) Tree, based on Medical Subject Headings (MeSH). Using the 2006 and 2007 TREC Genomics track data, we have evaluated the performance of the eCMeSH Tree in expanding queries. We have compared our results to those obtained using two other approaches, i.e. pseudo-relevance feedback (PRF) and document translation (DT). Subsequently, we evaluate the performance of different combinations of these three retrieval methods. Our results show that our method of expanding queries using the eCMeSH Tree can outperform the PRF method. Furthermore, combining this method with PRF and DT helps to smooth the differences in query expansion, and consequently results in the best performance amongst all experiments reported. All experiments compare the use of two different retrieval models, i.e. Okapi BM25 and a query likelihood language model. In general, the former performs slightly better.</abstract>
<identifier type="citekey">wang-etal-2012-biomedical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/316_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1148</start>
<end>1155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Biomedical Chinese-English CLIR Using an Extended CMeSH Resource to Expand Queries
%A Wang, Xinkai
%A Thompson, Paul
%A Tsujii, Jun’ichi
%A Ananiadou, Sophia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F wang-etal-2012-biomedical
%X Cross-lingual information retrieval (CLIR) involving the Chinese language has been thoroughly studied in the general language domain, but rarely in the biomedical domain, due to the lack of suitable linguistic resources and parsing tools. In this paper, we describe a Chinese-English CLIR system for biomedical literature, which exploits a bilingual ontology, the “eCMeSH Tree””””. This is an extension of the Chinese Medical Subject Headings (CMeSH) Tree, based on Medical Subject Headings (MeSH). Using the 2006 and 2007 TREC Genomics track data, we have evaluated the performance of the eCMeSH Tree in expanding queries. We have compared our results to those obtained using two other approaches, i.e. pseudo-relevance feedback (PRF) and document translation (DT). Subsequently, we evaluate the performance of different combinations of these three retrieval methods. Our results show that our method of expanding queries using the eCMeSH Tree can outperform the PRF method. Furthermore, combining this method with PRF and DT helps to smooth the differences in query expansion, and consequently results in the best performance amongst all experiments reported. All experiments compare the use of two different retrieval models, i.e. Okapi BM25 and a query likelihood language model. In general, the former performs slightly better.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/316_Paper.pdf
%P 1148-1155
Markdown (Informal)
[Biomedical Chinese-English CLIR Using an Extended CMeSH Resource to Expand Queries](http://www.lrec-conf.org/proceedings/lrec2012/pdf/316_Paper.pdf) (Wang et al., LREC 2012)
ACL