@inproceedings{han-etal-2020-multimwe,
title = "{M}ulti{MWE}: Building a Multi-lingual Multi-Word Expression ({MWE}) Parallel Corpora",
author = "Han, Lifeng and
Jones, Gareth and
Smeaton, Alan",
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-1.363",
pages = "2970--2979",
abstract = "Multi-word expressions (MWEs) are a hot topic in research in natural language processing (NLP), including topics such as MWE detection, MWE decomposition, and research investigating the exploitation of MWEs in other NLP fields such as Machine Translation. However, the availability of bilingual or multi-lingual MWE corpora is very limited. The only bilingual MWE corpora that we are aware of is from the PARSEME (PARSing and Multi-word Expressions) EU Project. This is a small collection of only 871 pairs of English-German MWEs. In this paper, we present multi-lingual and bilingual MWE corpora that we have extracted from root parallel corpora. Our collections are 3,159,226 and 143,042 bilingual MWE pairs for German-English and Chinese-English respectively after filtering. We examine the quality of these extracted bilingual MWEs in MT experiments. Our initial experiments applying MWEs in MT show improved translation performances on MWE terms in qualitative analysis and better general evaluation scores in quantitative analysis, on both German-English and Chinese-English language pairs. We follow a standard experimental pipeline to create our MultiMWE corpora which are available online. Researchers can use this free corpus for their own models or use them in a knowledge base as model features.",
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="han-etal-2020-multimwe">
<titleInfo>
<title>MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gareth</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Smeaton</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>Multi-word expressions (MWEs) are a hot topic in research in natural language processing (NLP), including topics such as MWE detection, MWE decomposition, and research investigating the exploitation of MWEs in other NLP fields such as Machine Translation. However, the availability of bilingual or multi-lingual MWE corpora is very limited. The only bilingual MWE corpora that we are aware of is from the PARSEME (PARSing and Multi-word Expressions) EU Project. This is a small collection of only 871 pairs of English-German MWEs. In this paper, we present multi-lingual and bilingual MWE corpora that we have extracted from root parallel corpora. Our collections are 3,159,226 and 143,042 bilingual MWE pairs for German-English and Chinese-English respectively after filtering. We examine the quality of these extracted bilingual MWEs in MT experiments. Our initial experiments applying MWEs in MT show improved translation performances on MWE terms in qualitative analysis and better general evaluation scores in quantitative analysis, on both German-English and Chinese-English language pairs. We follow a standard experimental pipeline to create our MultiMWE corpora which are available online. Researchers can use this free corpus for their own models or use them in a knowledge base as model features.</abstract>
<identifier type="citekey">han-etal-2020-multimwe</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.363</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2970</start>
<end>2979</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora
%A Han, Lifeng
%A Jones, Gareth
%A Smeaton, Alan
%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 han-etal-2020-multimwe
%X Multi-word expressions (MWEs) are a hot topic in research in natural language processing (NLP), including topics such as MWE detection, MWE decomposition, and research investigating the exploitation of MWEs in other NLP fields such as Machine Translation. However, the availability of bilingual or multi-lingual MWE corpora is very limited. The only bilingual MWE corpora that we are aware of is from the PARSEME (PARSing and Multi-word Expressions) EU Project. This is a small collection of only 871 pairs of English-German MWEs. In this paper, we present multi-lingual and bilingual MWE corpora that we have extracted from root parallel corpora. Our collections are 3,159,226 and 143,042 bilingual MWE pairs for German-English and Chinese-English respectively after filtering. We examine the quality of these extracted bilingual MWEs in MT experiments. Our initial experiments applying MWEs in MT show improved translation performances on MWE terms in qualitative analysis and better general evaluation scores in quantitative analysis, on both German-English and Chinese-English language pairs. We follow a standard experimental pipeline to create our MultiMWE corpora which are available online. Researchers can use this free corpus for their own models or use them in a knowledge base as model features.
%U https://aclanthology.org/2020.lrec-1.363
%P 2970-2979
Markdown (Informal)
[MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora](https://aclanthology.org/2020.lrec-1.363) (Han et al., LREC 2020)
ACL