@inproceedings{silvestre-baquero-mitkov-2017-translation,
title = "Translation Memory Systems Have a Long Way to Go",
author = "Silvestre Baquero, Andrea and
Mitkov, Ruslan",
editor = "Temnikova, Irina and
Orasan, Constantin and
Pastor, Gloria Corpas and
Vogel, Stephan",
booktitle = "Proceedings of the Workshop Human-Informed Translation and Interpreting Technology",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "Association for Computational Linguistics, Shoumen, Bulgaria",
url = "https://doi.org/10.26615/978-954-452-042-7_006",
doi = "10.26615/978-954-452-042-7_006",
pages = "44--51",
abstract = "The TM memory systems changed the work of translators and now the translators not benefiting from these tools are a tiny minority. These tools operate on fuzzy (surface) matching mostly and cannot benefit from already translated texts which are synonymous to (or paraphrased versions of) the text to be translated. The match score is mostly based on character-string similarity, calculated through Levenshtein distance. The TM tools have difficulties with detecting similarities even in sentences which represent a minor revision of sentences already available in the translation memory. This shortcoming of the current TM systems was the subject of the present study and was empirically proven in the experiments we conducted. To this end, we compiled a small translation memory (English-Spanish) and applied several lexical and syntactic transformation rules to the source sentences with both English and Spanish being the source language. The results of this study show that current TM systems have a long way to go and highlight the need for TM systems equipped with NLP capabilities which will offer the translator the advantage of he/she not having to translate a sentence again if an almost identical sentence has already been already translated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silvestre-baquero-mitkov-2017-translation">
<titleInfo>
<title>Translation Memory Systems Have a Long Way to Go</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Silvestre Baquero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop Human-Informed Translation and Interpreting Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Temnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantin</namePart>
<namePart type="family">Orasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gloria</namePart>
<namePart type="given">Corpas</namePart>
<namePart type="family">Pastor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Vogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics, Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The TM memory systems changed the work of translators and now the translators not benefiting from these tools are a tiny minority. These tools operate on fuzzy (surface) matching mostly and cannot benefit from already translated texts which are synonymous to (or paraphrased versions of) the text to be translated. The match score is mostly based on character-string similarity, calculated through Levenshtein distance. The TM tools have difficulties with detecting similarities even in sentences which represent a minor revision of sentences already available in the translation memory. This shortcoming of the current TM systems was the subject of the present study and was empirically proven in the experiments we conducted. To this end, we compiled a small translation memory (English-Spanish) and applied several lexical and syntactic transformation rules to the source sentences with both English and Spanish being the source language. The results of this study show that current TM systems have a long way to go and highlight the need for TM systems equipped with NLP capabilities which will offer the translator the advantage of he/she not having to translate a sentence again if an almost identical sentence has already been already translated.</abstract>
<identifier type="citekey">silvestre-baquero-mitkov-2017-translation</identifier>
<identifier type="doi">10.26615/978-954-452-042-7_006</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>44</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation Memory Systems Have a Long Way to Go
%A Silvestre Baquero, Andrea
%A Mitkov, Ruslan
%Y Temnikova, Irina
%Y Orasan, Constantin
%Y Pastor, Gloria Corpas
%Y Vogel, Stephan
%S Proceedings of the Workshop Human-Informed Translation and Interpreting Technology
%D 2017
%8 September
%I Association for Computational Linguistics, Shoumen, Bulgaria
%C Varna, Bulgaria
%F silvestre-baquero-mitkov-2017-translation
%X The TM memory systems changed the work of translators and now the translators not benefiting from these tools are a tiny minority. These tools operate on fuzzy (surface) matching mostly and cannot benefit from already translated texts which are synonymous to (or paraphrased versions of) the text to be translated. The match score is mostly based on character-string similarity, calculated through Levenshtein distance. The TM tools have difficulties with detecting similarities even in sentences which represent a minor revision of sentences already available in the translation memory. This shortcoming of the current TM systems was the subject of the present study and was empirically proven in the experiments we conducted. To this end, we compiled a small translation memory (English-Spanish) and applied several lexical and syntactic transformation rules to the source sentences with both English and Spanish being the source language. The results of this study show that current TM systems have a long way to go and highlight the need for TM systems equipped with NLP capabilities which will offer the translator the advantage of he/she not having to translate a sentence again if an almost identical sentence has already been already translated.
%R 10.26615/978-954-452-042-7_006
%U https://doi.org/10.26615/978-954-452-042-7_006
%P 44-51
Markdown (Informal)
[Translation Memory Systems Have a Long Way to Go](https://doi.org/10.26615/978-954-452-042-7_006) (Silvestre Baquero & Mitkov, RANLP 2017)
ACL
- Andrea Silvestre Baquero and Ruslan Mitkov. 2017. Translation Memory Systems Have a Long Way to Go. In Proceedings of the Workshop Human-Informed Translation and Interpreting Technology, pages 44–51, Varna, Bulgaria. Association for Computational Linguistics, Shoumen, Bulgaria.