@inproceedings{silva-etal-2012-dealing,
title = "Dealing with unknown words in statistical machine translation",
author = "Silva, Jo{\~a}o and
Coheur, Lu{\'\i}sa and
Costa, {\^A}ngela and
Trancoso, Isabel",
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/980_Paper.pdf",
pages = "3911--3981",
abstract = "In Statistical Machine Translation, words that were not seen during training are unknown words, that is, words that the system will not know how to translate. In this paper we contribute to this research problem by profiting from orthographic cues given by words. Thus, we report a study of the impact of word distance metrics in cognates' detection and, in addition, on the possibility of obtaining possible translations of unknown words through Logical Analogy. Our approach is tested in the translation of corpora from Portuguese to English (and vice-versa).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silva-etal-2012-dealing">
<titleInfo>
<title>Dealing with unknown words in statistical machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luísa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ângela</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</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 Statistical Machine Translation, words that were not seen during training are unknown words, that is, words that the system will not know how to translate. In this paper we contribute to this research problem by profiting from orthographic cues given by words. Thus, we report a study of the impact of word distance metrics in cognates’ detection and, in addition, on the possibility of obtaining possible translations of unknown words through Logical Analogy. Our approach is tested in the translation of corpora from Portuguese to English (and vice-versa).</abstract>
<identifier type="citekey">silva-etal-2012-dealing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/980_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3911</start>
<end>3981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dealing with unknown words in statistical machine translation
%A Silva, João
%A Coheur, Luísa
%A Costa, Ângela
%A Trancoso, Isabel
%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 silva-etal-2012-dealing
%X In Statistical Machine Translation, words that were not seen during training are unknown words, that is, words that the system will not know how to translate. In this paper we contribute to this research problem by profiting from orthographic cues given by words. Thus, we report a study of the impact of word distance metrics in cognates’ detection and, in addition, on the possibility of obtaining possible translations of unknown words through Logical Analogy. Our approach is tested in the translation of corpora from Portuguese to English (and vice-versa).
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/980_Paper.pdf
%P 3911-3981
Markdown (Informal)
[Dealing with unknown words in statistical machine translation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/980_Paper.pdf) (Silva et al., LREC 2012)
ACL
- João Silva, Luísa Coheur, Ângela Costa, and Isabel Trancoso. 2012. Dealing with unknown words in statistical machine translation. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3911–3981, Istanbul, Turkey. European Language Resources Association (ELRA).