@inproceedings{wolff-etal-2014-missed,
title = "Missed opportunities in translation memory matching",
author = "Wolff, Friedel and
Pretorius, Laurette and
Buitelaar, Paul",
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/1061_Paper.pdf",
pages = "4401--4406",
abstract = "A translation memory system stores a data set of source-target pairs of translations. It attempts to respond to a query in the source language with a useful target text from the data set to assist a human translator. Such systems estimate the usefulness of a target text suggestion according to the similarity of its associated source text to the source text query. This study analyses two data sets in two language pairs each to find highly similar target texts, which would be useful mutual suggestions. We further investigate which of these useful suggestions can not be selected through source text similarity, and we do a thorough analysis of these cases to categorise and quantify them. This analysis provides insight into areas where the recall of translation memory systems can be improved. Specifically, source texts with an omission, and semantically very similar source texts are some of the more frequent cases with useful target text suggestions that are not selected with the baseline approach of simple edit distance between the source texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wolff-etal-2014-missed">
<titleInfo>
<title>Missed opportunities in translation memory matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Friedel</namePart>
<namePart type="family">Wolff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurette</namePart>
<namePart type="family">Pretorius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</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>A translation memory system stores a data set of source-target pairs of translations. It attempts to respond to a query in the source language with a useful target text from the data set to assist a human translator. Such systems estimate the usefulness of a target text suggestion according to the similarity of its associated source text to the source text query. This study analyses two data sets in two language pairs each to find highly similar target texts, which would be useful mutual suggestions. We further investigate which of these useful suggestions can not be selected through source text similarity, and we do a thorough analysis of these cases to categorise and quantify them. This analysis provides insight into areas where the recall of translation memory systems can be improved. Specifically, source texts with an omission, and semantically very similar source texts are some of the more frequent cases with useful target text suggestions that are not selected with the baseline approach of simple edit distance between the source texts.</abstract>
<identifier type="citekey">wolff-etal-2014-missed</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1061_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4401</start>
<end>4406</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Missed opportunities in translation memory matching
%A Wolff, Friedel
%A Pretorius, Laurette
%A Buitelaar, Paul
%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 wolff-etal-2014-missed
%X A translation memory system stores a data set of source-target pairs of translations. It attempts to respond to a query in the source language with a useful target text from the data set to assist a human translator. Such systems estimate the usefulness of a target text suggestion according to the similarity of its associated source text to the source text query. This study analyses two data sets in two language pairs each to find highly similar target texts, which would be useful mutual suggestions. We further investigate which of these useful suggestions can not be selected through source text similarity, and we do a thorough analysis of these cases to categorise and quantify them. This analysis provides insight into areas where the recall of translation memory systems can be improved. Specifically, source texts with an omission, and semantically very similar source texts are some of the more frequent cases with useful target text suggestions that are not selected with the baseline approach of simple edit distance between the source texts.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1061_Paper.pdf
%P 4401-4406
Markdown (Informal)
[Missed opportunities in translation memory matching](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1061_Paper.pdf) (Wolff et al., LREC 2014)
ACL
- Friedel Wolff, Laurette Pretorius, and Paul Buitelaar. 2014. Missed opportunities in translation memory matching. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4401–4406, Reykjavik, Iceland. European Language Resources Association (ELRA).