@inproceedings{santos-simoes-2008-portuguese,
title = "{P}ortuguese-{E}nglish Word Alignment: some Experiments",
author = "Santos, Diana and
Sim{\~o}es, Alberto",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/760_paper.pdf",
abstract = "In this paper we describe some studies of Portuguese-English word alignment, focusing on (i) measuring the importance of the coupling between dictionaries and corpus; (ii) assessing the relevance of using syntactic information (POS and lemma) or just word forms, and (iii) taking into account the direction of translation. We first provide some motivation for the studies, as well as insist in separating type from token anlignment. We then briefly describe the resources employed: the EuroParl and COMPARA corpora, and the alignment tools, NATools, introducing some measures to evaluate the two kinds of dictionaries obtained. We then present the results of several experiments, comparing sizes, overlap, translation fertility and alignment density of the several bilingual resources built. We also describe preliminary data as far as quality of the resulting dictionaries or alignment results is concerned.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santos-simoes-2008-portuguese">
<titleInfo>
<title>Portuguese-English Word Alignment: some Experiments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Simões</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe some studies of Portuguese-English word alignment, focusing on (i) measuring the importance of the coupling between dictionaries and corpus; (ii) assessing the relevance of using syntactic information (POS and lemma) or just word forms, and (iii) taking into account the direction of translation. We first provide some motivation for the studies, as well as insist in separating type from token anlignment. We then briefly describe the resources employed: the EuroParl and COMPARA corpora, and the alignment tools, NATools, introducing some measures to evaluate the two kinds of dictionaries obtained. We then present the results of several experiments, comparing sizes, overlap, translation fertility and alignment density of the several bilingual resources built. We also describe preliminary data as far as quality of the resulting dictionaries or alignment results is concerned.</abstract>
<identifier type="citekey">santos-simoes-2008-portuguese</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/760_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Portuguese-English Word Alignment: some Experiments
%A Santos, Diana
%A Simões, Alberto
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F santos-simoes-2008-portuguese
%X In this paper we describe some studies of Portuguese-English word alignment, focusing on (i) measuring the importance of the coupling between dictionaries and corpus; (ii) assessing the relevance of using syntactic information (POS and lemma) or just word forms, and (iii) taking into account the direction of translation. We first provide some motivation for the studies, as well as insist in separating type from token anlignment. We then briefly describe the resources employed: the EuroParl and COMPARA corpora, and the alignment tools, NATools, introducing some measures to evaluate the two kinds of dictionaries obtained. We then present the results of several experiments, comparing sizes, overlap, translation fertility and alignment density of the several bilingual resources built. We also describe preliminary data as far as quality of the resulting dictionaries or alignment results is concerned.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/760_paper.pdf
Markdown (Informal)
[Portuguese-English Word Alignment: some Experiments](http://www.lrec-conf.org/proceedings/lrec2008/pdf/760_paper.pdf) (Santos & Simões, LREC 2008)
ACL
- Diana Santos and Alberto Simões. 2008. Portuguese-English Word Alignment: some Experiments. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).