@inproceedings{sanchez-cartagena-etal-2012-source,
title = "Source-Language Dictionaries Help Non-Expert Users to Enlarge Target-Language Dictionaries for Machine Translation",
author = "S{\'a}nchez-Cartagena, V{\'\i}ctor M. and
Espl{\`a}-Gomis, Miquel and
P{\'e}rez-Ortiz, Juan Antonio",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/527_Paper.pdf",
pages = "3422--3429",
abstract = "In this paper, a previous work on the enlargement of monolingual dictionaries of rule-based machine translation systems by non-expert users is extended to tackle the complete task of adding both source-language and target-language words to the monolingual dictionaries and the bilingual dictionary. In the original method, users validate whether some suffix variations of the word to be inserted are correct in order to find the most appropriate inflection paradigm. This method is now improved by taking advantage from the strong correlation detected between paradigms in both languages to reduce the search space of the target-language paradigm once the source-language paradigm is known. Results show that, when the source-language word has already been inserted, the system is able to more accurately predict which is the right target-language paradigm, and the number of queries posed to users is significantly reduced. Experiments also show that, when the source language and the target language are not closely related, it is only the source-language part-of-speech category, but not the rest of information provided by the source-language paradigm, which helps to correctly classify the target-language word.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-cartagena-etal-2012-source">
<titleInfo>
<title>Source-Language Dictionaries Help Non-Expert Users to Enlarge Target-Language Dictionaries for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, a previous work on the enlargement of monolingual dictionaries of rule-based machine translation systems by non-expert users is extended to tackle the complete task of adding both source-language and target-language words to the monolingual dictionaries and the bilingual dictionary. In the original method, users validate whether some suffix variations of the word to be inserted are correct in order to find the most appropriate inflection paradigm. This method is now improved by taking advantage from the strong correlation detected between paradigms in both languages to reduce the search space of the target-language paradigm once the source-language paradigm is known. Results show that, when the source-language word has already been inserted, the system is able to more accurately predict which is the right target-language paradigm, and the number of queries posed to users is significantly reduced. Experiments also show that, when the source language and the target language are not closely related, it is only the source-language part-of-speech category, but not the rest of information provided by the source-language paradigm, which helps to correctly classify the target-language word.</abstract>
<identifier type="citekey">sanchez-cartagena-etal-2012-source</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/527_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3422</start>
<end>3429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Source-Language Dictionaries Help Non-Expert Users to Enlarge Target-Language Dictionaries for Machine Translation
%A Sánchez-Cartagena, Víctor M.
%A Esplà-Gomis, Miquel
%A Pérez-Ortiz, Juan Antonio
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F sanchez-cartagena-etal-2012-source
%X In this paper, a previous work on the enlargement of monolingual dictionaries of rule-based machine translation systems by non-expert users is extended to tackle the complete task of adding both source-language and target-language words to the monolingual dictionaries and the bilingual dictionary. In the original method, users validate whether some suffix variations of the word to be inserted are correct in order to find the most appropriate inflection paradigm. This method is now improved by taking advantage from the strong correlation detected between paradigms in both languages to reduce the search space of the target-language paradigm once the source-language paradigm is known. Results show that, when the source-language word has already been inserted, the system is able to more accurately predict which is the right target-language paradigm, and the number of queries posed to users is significantly reduced. Experiments also show that, when the source language and the target language are not closely related, it is only the source-language part-of-speech category, but not the rest of information provided by the source-language paradigm, which helps to correctly classify the target-language word.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/527_Paper.pdf
%P 3422-3429
Markdown (Informal)
[Source-Language Dictionaries Help Non-Expert Users to Enlarge Target-Language Dictionaries for Machine Translation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/527_Paper.pdf) (Sánchez-Cartagena et al., LREC 2012)
ACL