@inproceedings{sidorov-etal-2010-english,
title = "{E}nglish-{S}panish Large Statistical Dictionary of Inflectional Forms",
author = "Sidorov, Grigori and
Barr{\'o}n-Cede{\~n}o, Alberto and
Rosso, Paolo",
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/229_Paper.pdf",
abstract = "The paper presents an approach for constructing a weighted bilingual dictionary of inflectional forms using as input data a traditional bilingual dictionary, and not parallel corpora. An algorithm is developed that generates all possible morphological (inflectional) forms and weights them using information on distribution of corresponding grammar sets (grammar information) in large corpora for each language. The algorithm also takes into account the compatibility of grammar sets in a language pair; for example, verb in past tense in language L normally is expected to be translated by verb in past tense in Language L'. We consider that the developed method is universal, i.e. can be applied to any pair of languages. The obtained dictionary is freely available. It can be used in several NLP tasks, for example, statistical machine translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sidorov-etal-2010-english">
<titleInfo>
<title>English-Spanish Large Statistical Dictionary of Inflectional Forms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Rosso</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>The paper presents an approach for constructing a weighted bilingual dictionary of inflectional forms using as input data a traditional bilingual dictionary, and not parallel corpora. An algorithm is developed that generates all possible morphological (inflectional) forms and weights them using information on distribution of corresponding grammar sets (grammar information) in large corpora for each language. The algorithm also takes into account the compatibility of grammar sets in a language pair; for example, verb in past tense in language L normally is expected to be translated by verb in past tense in Language L’. We consider that the developed method is universal, i.e. can be applied to any pair of languages. The obtained dictionary is freely available. It can be used in several NLP tasks, for example, statistical machine translation.</abstract>
<identifier type="citekey">sidorov-etal-2010-english</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/229_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English-Spanish Large Statistical Dictionary of Inflectional Forms
%A Sidorov, Grigori
%A Barrón-Cedeño, Alberto
%A Rosso, Paolo
%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 sidorov-etal-2010-english
%X The paper presents an approach for constructing a weighted bilingual dictionary of inflectional forms using as input data a traditional bilingual dictionary, and not parallel corpora. An algorithm is developed that generates all possible morphological (inflectional) forms and weights them using information on distribution of corresponding grammar sets (grammar information) in large corpora for each language. The algorithm also takes into account the compatibility of grammar sets in a language pair; for example, verb in past tense in language L normally is expected to be translated by verb in past tense in Language L’. We consider that the developed method is universal, i.e. can be applied to any pair of languages. The obtained dictionary is freely available. It can be used in several NLP tasks, for example, statistical machine translation.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/229_Paper.pdf
Markdown (Informal)
[English-Spanish Large Statistical Dictionary of Inflectional Forms](http://www.lrec-conf.org/proceedings/lrec2010/pdf/229_Paper.pdf) (Sidorov et al., LREC 2010)
ACL