@inproceedings{hoste-etal-2008-learning,
title = "Learning-based Detection of Scientific Terms in Patient Information",
author = "Hoste, Veronique and
Lefever, Els and
Vanopstal, Klaar and
Delaere, Isabelle",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/154_paper.pdf",
abstract = "In this paper, we investigate the use of a machine-learning based approach to the specific problem of scientific term detection in patient information. Lacking lexical databases which differentiate between the scientific and popular nature of medical terms, we used local context, morphosyntactic, morphological and statistical information to design a learner which accurately detects scientific medical terms. This study is the first step towards the automatic replacement of a scientific term by its popular counterpart, which should have a beneficial effect on readability. We show a F-score of 84{\%} for the prediction of scientific terms in an English and Dutch EPAR corpus. Since recasting the term extraction problem as a classification problem leads to a large skewedness of the resulting data set, we rebalanced the data set through the application of some simple TF-IDF-based and Log-likelihood-based filters. We show that filtering indeed has a beneficial effect on the learners performance. However, the results of the filtering approach combined with the learning-based approach remain below those of the learning-based approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoste-etal-2008-learning">
<titleInfo>
<title>Learning-based Detection of Scientific Terms in Patient Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klaar</namePart>
<namePart type="family">Vanopstal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Delaere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we investigate the use of a machine-learning based approach to the specific problem of scientific term detection in patient information. Lacking lexical databases which differentiate between the scientific and popular nature of medical terms, we used local context, morphosyntactic, morphological and statistical information to design a learner which accurately detects scientific medical terms. This study is the first step towards the automatic replacement of a scientific term by its popular counterpart, which should have a beneficial effect on readability. We show a F-score of 84% for the prediction of scientific terms in an English and Dutch EPAR corpus. Since recasting the term extraction problem as a classification problem leads to a large skewedness of the resulting data set, we rebalanced the data set through the application of some simple TF-IDF-based and Log-likelihood-based filters. We show that filtering indeed has a beneficial effect on the learners performance. However, the results of the filtering approach combined with the learning-based approach remain below those of the learning-based approach.</abstract>
<identifier type="citekey">hoste-etal-2008-learning</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/154_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning-based Detection of Scientific Terms in Patient Information
%A Hoste, Veronique
%A Lefever, Els
%A Vanopstal, Klaar
%A Delaere, Isabelle
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F hoste-etal-2008-learning
%X In this paper, we investigate the use of a machine-learning based approach to the specific problem of scientific term detection in patient information. Lacking lexical databases which differentiate between the scientific and popular nature of medical terms, we used local context, morphosyntactic, morphological and statistical information to design a learner which accurately detects scientific medical terms. This study is the first step towards the automatic replacement of a scientific term by its popular counterpart, which should have a beneficial effect on readability. We show a F-score of 84% for the prediction of scientific terms in an English and Dutch EPAR corpus. Since recasting the term extraction problem as a classification problem leads to a large skewedness of the resulting data set, we rebalanced the data set through the application of some simple TF-IDF-based and Log-likelihood-based filters. We show that filtering indeed has a beneficial effect on the learners performance. However, the results of the filtering approach combined with the learning-based approach remain below those of the learning-based approach.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/154_paper.pdf
Markdown (Informal)
[Learning-based Detection of Scientific Terms in Patient Information](http://www.lrec-conf.org/proceedings/lrec2008/pdf/154_paper.pdf) (Hoste et al., LREC 2008)
ACL