@inproceedings{mubarak-etal-2020-constructing,
title = "Constructing a Bilingual Corpus of Parallel Tweets",
author = "Mubarak, Hamdy and
Hassan, Sabit and
Abdelali, Ahmed",
editor = "Rapp, Reinhard and
Zweigenbaum, Pierre and
Sharoff, Serge",
booktitle = "Proceedings of the 13th Workshop on Building and Using Comparable Corpora",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.bucc-1.3",
pages = "14--21",
abstract = "In a bid to reach a larger and more diverse audience, Twitter users often post parallel tweets{---}tweets that contain the same content but are written in different languages. Parallel tweets can be an important resource for developing machine translation (MT) systems among other natural language processing (NLP) tasks. In this paper, we introduce a generic method for collecting parallel tweets. Using this method, we collect a bilingual corpus of English-Arabic parallel tweets and a list of Twitter accounts who post English-Arabictweets regularly. Since our method is generic, it can also be used for collecting parallel tweets that cover less-resourced languages such as Serbian and Urdu. Additionally, we annotate a subset of Twitter accounts with their countries of origin and topic of interest, which provides insights about the population who post parallel tweets. This latter information can also be useful for author profiling tasks.",
language = "English",
ISBN = "979-10-95546-42-9",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2020-constructing">
<titleInfo>
<title>Constructing a Bilingual Corpus of Parallel Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabit</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</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 13th Workshop on Building and Using Comparable Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</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">979-10-95546-42-9</identifier>
</relatedItem>
<abstract>In a bid to reach a larger and more diverse audience, Twitter users often post parallel tweets—tweets that contain the same content but are written in different languages. Parallel tweets can be an important resource for developing machine translation (MT) systems among other natural language processing (NLP) tasks. In this paper, we introduce a generic method for collecting parallel tweets. Using this method, we collect a bilingual corpus of English-Arabic parallel tweets and a list of Twitter accounts who post English-Arabictweets regularly. Since our method is generic, it can also be used for collecting parallel tweets that cover less-resourced languages such as Serbian and Urdu. Additionally, we annotate a subset of Twitter accounts with their countries of origin and topic of interest, which provides insights about the population who post parallel tweets. This latter information can also be useful for author profiling tasks.</abstract>
<identifier type="citekey">mubarak-etal-2020-constructing</identifier>
<location>
<url>https://aclanthology.org/2020.bucc-1.3</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>14</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Bilingual Corpus of Parallel Tweets
%A Mubarak, Hamdy
%A Hassan, Sabit
%A Abdelali, Ahmed
%Y Rapp, Reinhard
%Y Zweigenbaum, Pierre
%Y Sharoff, Serge
%S Proceedings of the 13th Workshop on Building and Using Comparable Corpora
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-42-9
%G English
%F mubarak-etal-2020-constructing
%X In a bid to reach a larger and more diverse audience, Twitter users often post parallel tweets—tweets that contain the same content but are written in different languages. Parallel tweets can be an important resource for developing machine translation (MT) systems among other natural language processing (NLP) tasks. In this paper, we introduce a generic method for collecting parallel tweets. Using this method, we collect a bilingual corpus of English-Arabic parallel tweets and a list of Twitter accounts who post English-Arabictweets regularly. Since our method is generic, it can also be used for collecting parallel tweets that cover less-resourced languages such as Serbian and Urdu. Additionally, we annotate a subset of Twitter accounts with their countries of origin and topic of interest, which provides insights about the population who post parallel tweets. This latter information can also be useful for author profiling tasks.
%U https://aclanthology.org/2020.bucc-1.3
%P 14-21
Markdown (Informal)
[Constructing a Bilingual Corpus of Parallel Tweets](https://aclanthology.org/2020.bucc-1.3) (Mubarak et al., BUCC 2020)
ACL
- Hamdy Mubarak, Sabit Hassan, and Ahmed Abdelali. 2020. Constructing a Bilingual Corpus of Parallel Tweets. In Proceedings of the 13th Workshop on Building and Using Comparable Corpora, pages 14–21, Marseille, France. European Language Resources Association.