@inproceedings{saad-etal-2014-building,
title = "Building and Modelling Multilingual Subjective Corpora",
author = {Saad, Motaz and
Langlois, David and
Sma{\"\i}li, Kamel},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/392_Paper.pdf",
pages = "3086--3091",
abstract = "Building multilingual opinionated models requires multilingual corpora annotated with opinion labels. Unfortunately, such kind of corpora are rare. We consider opinions in this work as subjective or objective. In this paper, we introduce an annotation method that can be reliably transferred across topic domains and across languages. The method starts by building a classifier that annotates sentences into subjective/objective label using a training data from {``}movie reviews{''} domain which is in English language. The annotation can be transferred to another language by classifying English sentences in parallel corpora and transferring the same annotation to the same sentences of the other language. We also shed the light on the link between opinion mining and statistical language modelling, and how such corpora are useful for domain specific language modelling. We show the distinction between subjective and objective sentences which tends to be stable across domains and languages. Our experiments show that language models trained on objective (respectively subjective) corpus lead to better perplexities on objective (respectively subjective) test.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saad-etal-2014-building">
<titleInfo>
<title>Building and Modelling Multilingual Subjective Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Motaz</namePart>
<namePart type="family">Saad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Langlois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamel</namePart>
<namePart type="family">Smaïli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building multilingual opinionated models requires multilingual corpora annotated with opinion labels. Unfortunately, such kind of corpora are rare. We consider opinions in this work as subjective or objective. In this paper, we introduce an annotation method that can be reliably transferred across topic domains and across languages. The method starts by building a classifier that annotates sentences into subjective/objective label using a training data from “movie reviews” domain which is in English language. The annotation can be transferred to another language by classifying English sentences in parallel corpora and transferring the same annotation to the same sentences of the other language. We also shed the light on the link between opinion mining and statistical language modelling, and how such corpora are useful for domain specific language modelling. We show the distinction between subjective and objective sentences which tends to be stable across domains and languages. Our experiments show that language models trained on objective (respectively subjective) corpus lead to better perplexities on objective (respectively subjective) test.</abstract>
<identifier type="citekey">saad-etal-2014-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/392_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3086</start>
<end>3091</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building and Modelling Multilingual Subjective Corpora
%A Saad, Motaz
%A Langlois, David
%A Smaïli, Kamel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F saad-etal-2014-building
%X Building multilingual opinionated models requires multilingual corpora annotated with opinion labels. Unfortunately, such kind of corpora are rare. We consider opinions in this work as subjective or objective. In this paper, we introduce an annotation method that can be reliably transferred across topic domains and across languages. The method starts by building a classifier that annotates sentences into subjective/objective label using a training data from “movie reviews” domain which is in English language. The annotation can be transferred to another language by classifying English sentences in parallel corpora and transferring the same annotation to the same sentences of the other language. We also shed the light on the link between opinion mining and statistical language modelling, and how such corpora are useful for domain specific language modelling. We show the distinction between subjective and objective sentences which tends to be stable across domains and languages. Our experiments show that language models trained on objective (respectively subjective) corpus lead to better perplexities on objective (respectively subjective) test.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/392_Paper.pdf
%P 3086-3091
Markdown (Informal)
[Building and Modelling Multilingual Subjective Corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/392_Paper.pdf) (Saad et al., LREC 2014)
ACL
- Motaz Saad, David Langlois, and Kamel Smaïli. 2014. Building and Modelling Multilingual Subjective Corpora. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3086–3091, Reykjavik, Iceland. European Language Resources Association (ELRA).