he European Commission’s (EC) Directorate General for Translation, together with the EC’s Joint Research Centre, is making
available a large translation memory (TM; i.e. sentences and their professionally produced translations) covering twenty-two official European Union (EU) languages and their 231 language pairs. Such a resource is typically used by translation professionals in
combination with TM software to improve speed and consistency of their translations. However, this resource has also many uses for translation studies and for language technology applications, including Statistical Machine Translation (SMT), terminology extraction, Named Entity Recognition (NER), multilingual classification and clustering, and many more. In this reference paper for DGT-TM, we introduce this new resource, provide statistics regarding its size, and explain how it was produced and how to use it.
%0 Conference Paper
%1 Steinberg2012
%A Steinberg, Ralph
%A Eisele, Andreas
%A Klocek, Szymon
%A Pilos, Spyridon
%A Schlüter, Patrick
%B LREC'2012
%C Istanbul
%D 2012
%K DGT comisión_europea memorias_de_traducción tecnologías_de_la_traducción
%P 454--459
%T DGT-TM: A freely Available Translation Memory in 22 Languages
%U http://arxiv.org/ftp/arxiv/papers/1309/1309.5226.pdf
%X he European Commission’s (EC) Directorate General for Translation, together with the EC’s Joint Research Centre, is making
available a large translation memory (TM; i.e. sentences and their professionally produced translations) covering twenty-two official European Union (EU) languages and their 231 language pairs. Such a resource is typically used by translation professionals in
combination with TM software to improve speed and consistency of their translations. However, this resource has also many uses for translation studies and for language technology applications, including Statistical Machine Translation (SMT), terminology extraction, Named Entity Recognition (NER), multilingual classification and clustering, and many more. In this reference paper for DGT-TM, we introduce this new resource, provide statistics regarding its size, and explain how it was produced and how to use it.
@inproceedings{Steinberg2012,
abstract = {he European Commission’s (EC) Directorate General for Translation, together with the EC’s Joint Research Centre, is making
available a large translation memory (TM; i.e. sentences and their professionally produced translations) covering twenty-two official European Union (EU) languages and their 231 language pairs. Such a resource is typically used by translation professionals in
combination with TM software to improve speed and consistency of their translations. However, this resource has also many uses for translation studies and for language technology applications, including Statistical Machine Translation (SMT), terminology extraction, Named Entity Recognition (NER), multilingual classification and clustering, and many more. In this reference paper for DGT-TM, we introduce this new resource, provide statistics regarding its size, and explain how it was produced and how to use it. },
added-at = {2015-12-09T21:07:47.000+0100},
address = {Istanbul},
author = {Steinberg, Ralph and Eisele, Andreas and Klocek, Szymon and Pilos, Spyridon and Schl{\"{u}}ter, Patrick},
biburl = {https://www.bibsonomy.org/bibtex/2f1b202be6c487d81834a865e5da5ab7b/evalopezsainz},
booktitle = {LREC'2012},
interhash = {70965cda92bada45fa8453a1985fd3d2},
intrahash = {f1b202be6c487d81834a865e5da5ab7b},
keywords = {DGT comisión_europea memorias_de_traducción tecnologías_de_la_traducción},
mendeley-tags = {electronic corpora,european commission,translation memory},
pages = {454--459},
timestamp = {2015-12-10T10:02:09.000+0100},
title = {{DGT-TM: A freely Available Translation Memory in 22 Languages }},
url = {http://arxiv.org/ftp/arxiv/papers/1309/1309.5226.pdf},
year = 2012
}