@inproceedings{chowdhury-lavelli-2012-evaluation,
title = "An Evaluation of the Effect of Automatic Preprocessing on Syntactic Parsing for Biomedical Relation Extraction",
author = "Chowdhury, Md. Faisal Mahbub and
Lavelli, Alberto",
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/522_Paper.pdf",
pages = "544--551",
abstract = "Relation extraction (RE) is an important text mining task which is the basis for further complex and advanced tasks. In state-of-the-art RE approaches, syntactic information obtained through parsing plays a crucial role. In the context of biomedical RE previous studies report usage of various automatic preprocessing techniques applied before parsing the input text. However, these studies do not specify to what extent such techniques improve RE results and to what extent they are corpus specific as well as parser specific. In this paper, we aim at addressing these issues by using various preprocessing techniques, two syntactic tree kernel based RE approaches and two different parsers on 5 widely used benchmark biomedical corpora of the protein-protein interaction (PPI) extraction task. We also provide analyses of various corpus characteristics to verify whether there are correlations between these characteristics and the RE results obtained. These analyses of corpus characteristics can be exploited to compare the 5 PPI corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-lavelli-2012-evaluation">
<titleInfo>
<title>An Evaluation of the Effect of Automatic Preprocessing on Syntactic Parsing for Biomedical Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Faisal</namePart>
<namePart type="given">Mahbub</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</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>Relation extraction (RE) is an important text mining task which is the basis for further complex and advanced tasks. In state-of-the-art RE approaches, syntactic information obtained through parsing plays a crucial role. In the context of biomedical RE previous studies report usage of various automatic preprocessing techniques applied before parsing the input text. However, these studies do not specify to what extent such techniques improve RE results and to what extent they are corpus specific as well as parser specific. In this paper, we aim at addressing these issues by using various preprocessing techniques, two syntactic tree kernel based RE approaches and two different parsers on 5 widely used benchmark biomedical corpora of the protein-protein interaction (PPI) extraction task. We also provide analyses of various corpus characteristics to verify whether there are correlations between these characteristics and the RE results obtained. These analyses of corpus characteristics can be exploited to compare the 5 PPI corpora.</abstract>
<identifier type="citekey">chowdhury-lavelli-2012-evaluation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/522_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>544</start>
<end>551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Evaluation of the Effect of Automatic Preprocessing on Syntactic Parsing for Biomedical Relation Extraction
%A Chowdhury, Md. Faisal Mahbub
%A Lavelli, Alberto
%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 chowdhury-lavelli-2012-evaluation
%X Relation extraction (RE) is an important text mining task which is the basis for further complex and advanced tasks. In state-of-the-art RE approaches, syntactic information obtained through parsing plays a crucial role. In the context of biomedical RE previous studies report usage of various automatic preprocessing techniques applied before parsing the input text. However, these studies do not specify to what extent such techniques improve RE results and to what extent they are corpus specific as well as parser specific. In this paper, we aim at addressing these issues by using various preprocessing techniques, two syntactic tree kernel based RE approaches and two different parsers on 5 widely used benchmark biomedical corpora of the protein-protein interaction (PPI) extraction task. We also provide analyses of various corpus characteristics to verify whether there are correlations between these characteristics and the RE results obtained. These analyses of corpus characteristics can be exploited to compare the 5 PPI corpora.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/522_Paper.pdf
%P 544-551
Markdown (Informal)
[An Evaluation of the Effect of Automatic Preprocessing on Syntactic Parsing for Biomedical Relation Extraction](http://www.lrec-conf.org/proceedings/lrec2012/pdf/522_Paper.pdf) (Chowdhury & Lavelli, LREC 2012)
ACL