@inproceedings{saralegi-lopez-de-lacalle-2010-dictionary,
title = "Dictionary and Monolingual Corpus-based Query Translation for {B}asque-{E}nglish {CLIR}",
author = "Saralegi, Xabier and
Lopez de Lacalle, Maddalen",
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/63_Paper.pdf",
abstract = {This paper deals with the main problems that arise in the query translation process in dictionary-based Cross-lingual Information Retrieval (CLIR): translation selection, presence of Out-Of-Vocabulary (OOV) terms and translation of Multi-Word Expressions (MWE). We analyse to what extent each problem affects the retrieval performance for the Basque-English pair of languages, and the improvement obtained when using parallel corpora free methods to address them. To tackle the translation selection problem we provide novel extensions of an already existing monolingual target co-occurrence-based method, the Out-Of Vocabulary terms are dealt with by means of a cognate detection-based method and finally, for the Multi-Word Expression translation problem, a na{\"\i}ve matching technique is applied. The error analysis shows significant differences in the deterioration of the performance depending on the problem, in terms of Mean Average Precision (MAP), the translation selection problem being the cause of most of the errors. Otherwise, the proposed combined strategy shows a good performance to tackle the three above-mentioned main problems.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saralegi-lopez-de-lacalle-2010-dictionary">
<titleInfo>
<title>Dictionary and Monolingual Corpus-based Query Translation for Basque-English CLIR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Saralegi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maddalen</namePart>
<namePart type="family">Lopez de Lacalle</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>This paper deals with the main problems that arise in the query translation process in dictionary-based Cross-lingual Information Retrieval (CLIR): translation selection, presence of Out-Of-Vocabulary (OOV) terms and translation of Multi-Word Expressions (MWE). We analyse to what extent each problem affects the retrieval performance for the Basque-English pair of languages, and the improvement obtained when using parallel corpora free methods to address them. To tackle the translation selection problem we provide novel extensions of an already existing monolingual target co-occurrence-based method, the Out-Of Vocabulary terms are dealt with by means of a cognate detection-based method and finally, for the Multi-Word Expression translation problem, a naïve matching technique is applied. The error analysis shows significant differences in the deterioration of the performance depending on the problem, in terms of Mean Average Precision (MAP), the translation selection problem being the cause of most of the errors. Otherwise, the proposed combined strategy shows a good performance to tackle the three above-mentioned main problems.</abstract>
<identifier type="citekey">saralegi-lopez-de-lacalle-2010-dictionary</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/63_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dictionary and Monolingual Corpus-based Query Translation for Basque-English CLIR
%A Saralegi, Xabier
%A Lopez de Lacalle, Maddalen
%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 saralegi-lopez-de-lacalle-2010-dictionary
%X This paper deals with the main problems that arise in the query translation process in dictionary-based Cross-lingual Information Retrieval (CLIR): translation selection, presence of Out-Of-Vocabulary (OOV) terms and translation of Multi-Word Expressions (MWE). We analyse to what extent each problem affects the retrieval performance for the Basque-English pair of languages, and the improvement obtained when using parallel corpora free methods to address them. To tackle the translation selection problem we provide novel extensions of an already existing monolingual target co-occurrence-based method, the Out-Of Vocabulary terms are dealt with by means of a cognate detection-based method and finally, for the Multi-Word Expression translation problem, a naïve matching technique is applied. The error analysis shows significant differences in the deterioration of the performance depending on the problem, in terms of Mean Average Precision (MAP), the translation selection problem being the cause of most of the errors. Otherwise, the proposed combined strategy shows a good performance to tackle the three above-mentioned main problems.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/63_Paper.pdf
Markdown (Informal)
[Dictionary and Monolingual Corpus-based Query Translation for Basque-English CLIR](http://www.lrec-conf.org/proceedings/lrec2010/pdf/63_Paper.pdf) (Saralegi & Lopez de Lacalle, LREC 2010)
ACL