@inproceedings{scherrer-sagot-2014-language,
title = "A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages",
author = "Scherrer, Yves and
Sagot, Beno{\^\i}t",
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/797_Paper.pdf",
pages = "502--508",
abstract = "In this paper, we describe our generic approach for transferring part-of-speech annotations from a resourced language towards an etymologically closely related non-resourced language, without using any bilingual (i.e., parallel) data. We first induce a translation lexicon from monolingual corpora, based on cognate detection followed by cross-lingual contextual similarity. Second, POS information is transferred from the resourced language along translation pairs to the non-resourced language and used for tagging the corpus. We evaluate our methods on three language families, consisting of five Romance languages, three Germanic languages and five Slavic languages. We obtain tagging accuracies of up to 91.6{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherrer-sagot-2014-language">
<titleInfo>
<title>A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</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>In this paper, we describe our generic approach for transferring part-of-speech annotations from a resourced language towards an etymologically closely related non-resourced language, without using any bilingual (i.e., parallel) data. We first induce a translation lexicon from monolingual corpora, based on cognate detection followed by cross-lingual contextual similarity. Second, POS information is transferred from the resourced language along translation pairs to the non-resourced language and used for tagging the corpus. We evaluate our methods on three language families, consisting of five Romance languages, three Germanic languages and five Slavic languages. We obtain tagging accuracies of up to 91.6%.</abstract>
<identifier type="citekey">scherrer-sagot-2014-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/797_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>502</start>
<end>508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages
%A Scherrer, Yves
%A Sagot, Benoît
%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 scherrer-sagot-2014-language
%X In this paper, we describe our generic approach for transferring part-of-speech annotations from a resourced language towards an etymologically closely related non-resourced language, without using any bilingual (i.e., parallel) data. We first induce a translation lexicon from monolingual corpora, based on cognate detection followed by cross-lingual contextual similarity. Second, POS information is transferred from the resourced language along translation pairs to the non-resourced language and used for tagging the corpus. We evaluate our methods on three language families, consisting of five Romance languages, three Germanic languages and five Slavic languages. We obtain tagging accuracies of up to 91.6%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/797_Paper.pdf
%P 502-508
Markdown (Informal)
[A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/797_Paper.pdf) (Scherrer & Sagot, LREC 2014)
ACL