@inproceedings{forcada-2014-annotation,
title = "On the annotation of {TMX} translation memories for advanced leveraging in computer-aided translation",
author = "Forcada, Mikel",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/373_Paper.pdf",
pages = "4374--4378",
abstract = "The term advanced leveraging refers to extensions beyond the current usage of translation memory (TM) in computer-aided translation (CAT). One of these extensions is the ability to identify and use matches on the sub-segment level ― for instance, using sub-sentential elements when segments are sentences― to help the translator when a reasonable fuzzy-matched proposal is not available; some such functionalities have started to become available in commercial CAT tools. Resources such as statistical word aligners, external machine translation systems, glossaries and term bases could be used to identify and annotate segment-level translation units at the sub-segment level, but there is currently no single, agreed standard supporting the interchange of sub-segmental annotation of translation memories to create a richer translation resource. This paper discusses the capabilities and limitations of some current standards, envisages possible alternatives, and ends with a tentative proposal which slightly abuses (repurposes) the usage of existing elements in the TMX standard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="forcada-2014-annotation">
<titleInfo>
<title>On the annotation of TMX translation memories for advanced leveraging in computer-aided translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The term advanced leveraging refers to extensions beyond the current usage of translation memory (TM) in computer-aided translation (CAT). One of these extensions is the ability to identify and use matches on the sub-segment level ― for instance, using sub-sentential elements when segments are sentences― to help the translator when a reasonable fuzzy-matched proposal is not available; some such functionalities have started to become available in commercial CAT tools. Resources such as statistical word aligners, external machine translation systems, glossaries and term bases could be used to identify and annotate segment-level translation units at the sub-segment level, but there is currently no single, agreed standard supporting the interchange of sub-segmental annotation of translation memories to create a richer translation resource. This paper discusses the capabilities and limitations of some current standards, envisages possible alternatives, and ends with a tentative proposal which slightly abuses (repurposes) the usage of existing elements in the TMX standard.</abstract>
<identifier type="citekey">forcada-2014-annotation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/373_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4374</start>
<end>4378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the annotation of TMX translation memories for advanced leveraging in computer-aided translation
%A Forcada, Mikel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F forcada-2014-annotation
%X The term advanced leveraging refers to extensions beyond the current usage of translation memory (TM) in computer-aided translation (CAT). One of these extensions is the ability to identify and use matches on the sub-segment level ― for instance, using sub-sentential elements when segments are sentences― to help the translator when a reasonable fuzzy-matched proposal is not available; some such functionalities have started to become available in commercial CAT tools. Resources such as statistical word aligners, external machine translation systems, glossaries and term bases could be used to identify and annotate segment-level translation units at the sub-segment level, but there is currently no single, agreed standard supporting the interchange of sub-segmental annotation of translation memories to create a richer translation resource. This paper discusses the capabilities and limitations of some current standards, envisages possible alternatives, and ends with a tentative proposal which slightly abuses (repurposes) the usage of existing elements in the TMX standard.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/373_Paper.pdf
%P 4374-4378
Markdown (Informal)
[On the annotation of TMX translation memories for advanced leveraging in computer-aided translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/373_Paper.pdf) (Forcada, LREC 2014)
ACL