@inproceedings{ahmed-etal-2020-multilingual,
title = "Multilingual Corpus Creation for Multilingual Semantic Similarity Task",
author = "Ahmed, Mahtab and
Dixit, Chahna and
Mercer, Robert E. and
Khan, Atif and
Samee, Muhammad Rifayat and
Urra, Felipe",
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-1.516",
pages = "4190--4196",
abstract = "In natural language processing, the performance of a semantic similarity task relies heavily on the availability of a large corpus. Various monolingual corpora are available (mainly English); but multilingual resources are very limited. In this work, we describe a semi-automated framework to create a multilingual corpus which can be used for the multilingual semantic similarity task. The similar sentence pairs are obtained by crawling bilingual websites, whereas the dissimilar sentence pairs are selected by applying topic modeling and an Open-AI GPT model on the similar sentence pairs. We focus on websites in the government, insurance, and banking domains to collect English-French and English-Spanish sentence pairs; however, this corpus creation approach can be applied to any other industry vertical provided that a bilingual website exists. We also show experimental results for multilingual semantic similarity to verify the quality of the corpus and demonstrate its usage.",
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="ahmed-etal-2020-multilingual">
<titleInfo>
<title>Multilingual Corpus Creation for Multilingual Semantic Similarity Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahtab</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chahna</namePart>
<namePart type="family">Dixit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Mercer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atif</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Rifayat</namePart>
<namePart type="family">Samee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Urra</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>In natural language processing, the performance of a semantic similarity task relies heavily on the availability of a large corpus. Various monolingual corpora are available (mainly English); but multilingual resources are very limited. In this work, we describe a semi-automated framework to create a multilingual corpus which can be used for the multilingual semantic similarity task. The similar sentence pairs are obtained by crawling bilingual websites, whereas the dissimilar sentence pairs are selected by applying topic modeling and an Open-AI GPT model on the similar sentence pairs. We focus on websites in the government, insurance, and banking domains to collect English-French and English-Spanish sentence pairs; however, this corpus creation approach can be applied to any other industry vertical provided that a bilingual website exists. We also show experimental results for multilingual semantic similarity to verify the quality of the corpus and demonstrate its usage.</abstract>
<identifier type="citekey">ahmed-etal-2020-multilingual</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.516</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4190</start>
<end>4196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Corpus Creation for Multilingual Semantic Similarity Task
%A Ahmed, Mahtab
%A Dixit, Chahna
%A Mercer, Robert E.
%A Khan, Atif
%A Samee, Muhammad Rifayat
%A Urra, Felipe
%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 ahmed-etal-2020-multilingual
%X In natural language processing, the performance of a semantic similarity task relies heavily on the availability of a large corpus. Various monolingual corpora are available (mainly English); but multilingual resources are very limited. In this work, we describe a semi-automated framework to create a multilingual corpus which can be used for the multilingual semantic similarity task. The similar sentence pairs are obtained by crawling bilingual websites, whereas the dissimilar sentence pairs are selected by applying topic modeling and an Open-AI GPT model on the similar sentence pairs. We focus on websites in the government, insurance, and banking domains to collect English-French and English-Spanish sentence pairs; however, this corpus creation approach can be applied to any other industry vertical provided that a bilingual website exists. We also show experimental results for multilingual semantic similarity to verify the quality of the corpus and demonstrate its usage.
%U https://aclanthology.org/2020.lrec-1.516
%P 4190-4196
Markdown (Informal)
[Multilingual Corpus Creation for Multilingual Semantic Similarity Task](https://aclanthology.org/2020.lrec-1.516) (Ahmed et al., LREC 2020)
ACL