@inproceedings{zhai-etal-2020-building,
title = "Building an {E}nglish-{C}hinese Parallel Corpus Annotated with Sub-sentential Translation Techniques",
author = "Zhai, Yuming and
Liu, Lufei and
Zhong, Xinyi and
Illouz, Gbariel and
Vilnat, Anne",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.496",
pages = "4024--4033",
abstract = "Human translators often resort to different non-literal translation techniques besides the literal translation, such as idiom equivalence, generalization, particularization, semantic modulation, etc., especially when the source and target languages have different and distant origins. Translation techniques constitute an important subject in translation studies, which help researchers to understand and analyse translated texts. However, they receive less attention in developing Natural Language Processing (NLP) applications. To fill this gap, one of our long term objectives is to have a better semantic control of extracting paraphrases from bilingual parallel corpora. Based on this goal, we suggest this hypothesis: it is possible to automatically recognize different sub-sentential translation techniques. For this original task, since there is no dedicated data set for English-Chinese, we manually annotated a parallel corpus of eleven genres. Fifty sentence pairs for each genre have been annotated in order to consolidate our annotation guidelines. Based on this data set, we conducted an experiment to classify between literal and non-literal translations. The preliminary results confirm our hypothesis. The corpus and code are available. We hope that this annotated corpus will be useful for linguistic contrastive studies and for fine-grained evaluation of NLP tasks, such as automatic word alignment and machine translation.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhai-etal-2020-building">
<titleInfo>
<title>Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuming</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lufei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gbariel</namePart>
<namePart type="family">Illouz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Vilnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Human translators often resort to different non-literal translation techniques besides the literal translation, such as idiom equivalence, generalization, particularization, semantic modulation, etc., especially when the source and target languages have different and distant origins. Translation techniques constitute an important subject in translation studies, which help researchers to understand and analyse translated texts. However, they receive less attention in developing Natural Language Processing (NLP) applications. To fill this gap, one of our long term objectives is to have a better semantic control of extracting paraphrases from bilingual parallel corpora. Based on this goal, we suggest this hypothesis: it is possible to automatically recognize different sub-sentential translation techniques. For this original task, since there is no dedicated data set for English-Chinese, we manually annotated a parallel corpus of eleven genres. Fifty sentence pairs for each genre have been annotated in order to consolidate our annotation guidelines. Based on this data set, we conducted an experiment to classify between literal and non-literal translations. The preliminary results confirm our hypothesis. The corpus and code are available. We hope that this annotated corpus will be useful for linguistic contrastive studies and for fine-grained evaluation of NLP tasks, such as automatic word alignment and machine translation.</abstract>
<identifier type="citekey">zhai-etal-2020-building</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.496</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4024</start>
<end>4033</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques
%A Zhai, Yuming
%A Liu, Lufei
%A Zhong, Xinyi
%A Illouz, Gbariel
%A Vilnat, Anne
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F zhai-etal-2020-building
%X Human translators often resort to different non-literal translation techniques besides the literal translation, such as idiom equivalence, generalization, particularization, semantic modulation, etc., especially when the source and target languages have different and distant origins. Translation techniques constitute an important subject in translation studies, which help researchers to understand and analyse translated texts. However, they receive less attention in developing Natural Language Processing (NLP) applications. To fill this gap, one of our long term objectives is to have a better semantic control of extracting paraphrases from bilingual parallel corpora. Based on this goal, we suggest this hypothesis: it is possible to automatically recognize different sub-sentential translation techniques. For this original task, since there is no dedicated data set for English-Chinese, we manually annotated a parallel corpus of eleven genres. Fifty sentence pairs for each genre have been annotated in order to consolidate our annotation guidelines. Based on this data set, we conducted an experiment to classify between literal and non-literal translations. The preliminary results confirm our hypothesis. The corpus and code are available. We hope that this annotated corpus will be useful for linguistic contrastive studies and for fine-grained evaluation of NLP tasks, such as automatic word alignment and machine translation.
%U https://aclanthology.org/2020.lrec-1.496
%P 4024-4033
Markdown (Informal)
[Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques](https://aclanthology.org/2020.lrec-1.496) (Zhai et al., LREC 2020)
ACL