@inproceedings{vicente-etal-2016-tweetmt,
title = "{T}weet{MT}: A Parallel Microblog Corpus",
author = "Vicente, I{\~n}aki San and
Alegr{\'\i}a, I{\~n}aki and
Espa{\~n}a-Bonet, Cristina and
Gamallo, Pablo and
Oliveira, Hugo Gon{\c{c}}alo and
Garcia, Eva Mart{\'\i}nez and
Toral, Antonio and
Zubiaga, Arkaitz and
Aranberri, Nora",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1469",
pages = "2936--2941",
abstract = "We introduce TweetMT, a parallel corpus of tweets in four language pairs that combine five languages (Spanish from/to Basque, Catalan, Galician and Portuguese), all of which have an official status in the Iberian Peninsula. The corpus has been created by combining automatic collection and crowdsourcing approaches, and it is publicly available. It is intended for the development and testing of microtext machine translation systems. In this paper we describe the methodology followed to build the corpus, and present the results of the shared task in which it was tested.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vicente-etal-2016-tweetmt">
<titleInfo>
<title>TweetMT: A Parallel Microblog Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="given">San</namePart>
<namePart type="family">Vicente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">Alegría</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España-Bonet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="given">Gonçalo</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="given">Martínez</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkaitz</namePart>
<namePart type="family">Zubiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce TweetMT, a parallel corpus of tweets in four language pairs that combine five languages (Spanish from/to Basque, Catalan, Galician and Portuguese), all of which have an official status in the Iberian Peninsula. The corpus has been created by combining automatic collection and crowdsourcing approaches, and it is publicly available. It is intended for the development and testing of microtext machine translation systems. In this paper we describe the methodology followed to build the corpus, and present the results of the shared task in which it was tested.</abstract>
<identifier type="citekey">vicente-etal-2016-tweetmt</identifier>
<location>
<url>https://aclanthology.org/L16-1469</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>2936</start>
<end>2941</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TweetMT: A Parallel Microblog Corpus
%A Vicente, Iñaki San
%A Alegría, Iñaki
%A España-Bonet, Cristina
%A Gamallo, Pablo
%A Oliveira, Hugo Gonçalo
%A Garcia, Eva Martínez
%A Toral, Antonio
%A Zubiaga, Arkaitz
%A Aranberri, Nora
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F vicente-etal-2016-tweetmt
%X We introduce TweetMT, a parallel corpus of tweets in four language pairs that combine five languages (Spanish from/to Basque, Catalan, Galician and Portuguese), all of which have an official status in the Iberian Peninsula. The corpus has been created by combining automatic collection and crowdsourcing approaches, and it is publicly available. It is intended for the development and testing of microtext machine translation systems. In this paper we describe the methodology followed to build the corpus, and present the results of the shared task in which it was tested.
%U https://aclanthology.org/L16-1469
%P 2936-2941
Markdown (Informal)
[TweetMT: A Parallel Microblog Corpus](https://aclanthology.org/L16-1469) (Vicente et al., LREC 2016)
ACL
- Iñaki San Vicente, Iñaki Alegría, Cristina España-Bonet, Pablo Gamallo, Hugo Gonçalo Oliveira, Eva Martínez Garcia, Antonio Toral, Arkaitz Zubiaga, and Nora Aranberri. 2016. TweetMT: A Parallel Microblog Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2936–2941, Portorož, Slovenia. European Language Resources Association (ELRA).