@inproceedings{bonin-etal-2010-contrastive,
title = "A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora",
author = "Bonin, Francesca and
Dell{'}Orletta, Felice and
Montemagni, Simonetta and
Venturi, Giulia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/553_Paper.pdf",
abstract = "In this paper, we present a novel approach to multi-word terminology extraction combining a well-known automatic term recognition approach, the C--NC value method, with a contrastive ranking technique, aimed at refining obtained results either by filtering noise due to common words or by discerning between semantically different types of terms within heterogeneous terminologies. Differently from other contrastive methods proposed in the literature that focus on single terms to overcome the multi-word terms' sparsity problem, the proposed contrastive function is able to handle variation in low frequency events by directly operating on pre-selected multi-word terms. This methodology has been tested in two case studies carried out in the History of Art and Legal domains. Evaluation of achieved results showed that the proposed two--stage approach improves significantly multi--word term extraction results. In particular, for what concerns the legal domain it provides an answer to a well-known problem in the semi--automatic construction of legal ontologies, namely that of singling out law terms from terms of the specific domain being regulated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bonin-etal-2010-contrastive">
<titleInfo>
<title>A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Bonin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Venturi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a novel approach to multi-word terminology extraction combining a well-known automatic term recognition approach, the C–NC value method, with a contrastive ranking technique, aimed at refining obtained results either by filtering noise due to common words or by discerning between semantically different types of terms within heterogeneous terminologies. Differently from other contrastive methods proposed in the literature that focus on single terms to overcome the multi-word terms’ sparsity problem, the proposed contrastive function is able to handle variation in low frequency events by directly operating on pre-selected multi-word terms. This methodology has been tested in two case studies carried out in the History of Art and Legal domains. Evaluation of achieved results showed that the proposed two–stage approach improves significantly multi–word term extraction results. In particular, for what concerns the legal domain it provides an answer to a well-known problem in the semi–automatic construction of legal ontologies, namely that of singling out law terms from terms of the specific domain being regulated.</abstract>
<identifier type="citekey">bonin-etal-2010-contrastive</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/553_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora
%A Bonin, Francesca
%A Dell’Orletta, Felice
%A Montemagni, Simonetta
%A Venturi, Giulia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F bonin-etal-2010-contrastive
%X In this paper, we present a novel approach to multi-word terminology extraction combining a well-known automatic term recognition approach, the C–NC value method, with a contrastive ranking technique, aimed at refining obtained results either by filtering noise due to common words or by discerning between semantically different types of terms within heterogeneous terminologies. Differently from other contrastive methods proposed in the literature that focus on single terms to overcome the multi-word terms’ sparsity problem, the proposed contrastive function is able to handle variation in low frequency events by directly operating on pre-selected multi-word terms. This methodology has been tested in two case studies carried out in the History of Art and Legal domains. Evaluation of achieved results showed that the proposed two–stage approach improves significantly multi–word term extraction results. In particular, for what concerns the legal domain it provides an answer to a well-known problem in the semi–automatic construction of legal ontologies, namely that of singling out law terms from terms of the specific domain being regulated.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/553_Paper.pdf
Markdown (Informal)
[A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora](http://www.lrec-conf.org/proceedings/lrec2010/pdf/553_Paper.pdf) (Bonin et al., LREC 2010)
ACL