@inproceedings{bouamor-etal-2012-contrastive,
title = "A contrastive review of paraphrase acquisition techniques",
author = "Bouamor, Houda and
Max, Aur{\'e}lien and
Illouz, Gabriel and
Vilnat, Anne",
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/555_Paper.pdf",
pages = "2653--2658",
abstract = "This paper addresses the issue of what approach should be used for building a corpus of sententential paraphrases depending on one's requirements. Six strategies are studied: (1) multiple translations into a single language from another language; (2) multiple translations into a single language from different other languages; (3) multiple descriptions of short videos; (4) multiple subtitles for the same language; (5) headlines for similar news articles; and (6) sub-sentential paraphrasing in the context of a Web-based game. We report results on French for 50 paraphrase pairs collected for all these strategies, where corpora were manually aligned at the finest possible level to define oracle performance in terms of accessible sub-sentential paraphrases. The differences observed will be used as criteria for motivating the choice of a given approach before attempting to build a new paraphrase corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bouamor-etal-2012-contrastive">
<titleInfo>
<title>A contrastive review of paraphrase acquisition techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélien</namePart>
<namePart type="family">Max</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Illouz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Vilnat</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>This paper addresses the issue of what approach should be used for building a corpus of sententential paraphrases depending on one’s requirements. Six strategies are studied: (1) multiple translations into a single language from another language; (2) multiple translations into a single language from different other languages; (3) multiple descriptions of short videos; (4) multiple subtitles for the same language; (5) headlines for similar news articles; and (6) sub-sentential paraphrasing in the context of a Web-based game. We report results on French for 50 paraphrase pairs collected for all these strategies, where corpora were manually aligned at the finest possible level to define oracle performance in terms of accessible sub-sentential paraphrases. The differences observed will be used as criteria for motivating the choice of a given approach before attempting to build a new paraphrase corpus.</abstract>
<identifier type="citekey">bouamor-etal-2012-contrastive</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/555_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2653</start>
<end>2658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A contrastive review of paraphrase acquisition techniques
%A Bouamor, Houda
%A Max, Aurélien
%A Illouz, Gabriel
%A Vilnat, Anne
%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 bouamor-etal-2012-contrastive
%X This paper addresses the issue of what approach should be used for building a corpus of sententential paraphrases depending on one’s requirements. Six strategies are studied: (1) multiple translations into a single language from another language; (2) multiple translations into a single language from different other languages; (3) multiple descriptions of short videos; (4) multiple subtitles for the same language; (5) headlines for similar news articles; and (6) sub-sentential paraphrasing in the context of a Web-based game. We report results on French for 50 paraphrase pairs collected for all these strategies, where corpora were manually aligned at the finest possible level to define oracle performance in terms of accessible sub-sentential paraphrases. The differences observed will be used as criteria for motivating the choice of a given approach before attempting to build a new paraphrase corpus.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/555_Paper.pdf
%P 2653-2658
Markdown (Informal)
[A contrastive review of paraphrase acquisition techniques](http://www.lrec-conf.org/proceedings/lrec2012/pdf/555_Paper.pdf) (Bouamor et al., LREC 2012)
ACL
- Houda Bouamor, Aurélien Max, Gabriel Illouz, and Anne Vilnat. 2012. A contrastive review of paraphrase acquisition techniques. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2653–2658, Istanbul, Turkey. European Language Resources Association (ELRA).