@inproceedings{gotti-etal-2014-hashtag,
title = "Hashtag Occurrences, Layout and Translation: A Corpus-driven Analysis of Tweets Published by the {C}anadian Government",
author = "Gotti, Fabrizio and
Langlais, Phillippe and
Farzindar, Atefeh",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/53_Paper.pdf",
pages = "2254--2261",
abstract = "We present an aligned bilingual corpus of 8758 tweet pairs in French and English, derived from Canadian government agencies. Hashtags appear in a tweet{'}s prologue, announcing its topic, or in the tweet{'}s text in lieu of traditional words, or in an epilogue. Hashtags are words prefixed with a pound sign in 80{\%} of the cases. The rest is mostly multiword hashtags, for which we describe a segmentation algorithm. A manual analysis of the bilingual alignment of 5000 hashtags shows that 5{\%} (French) to 18{\%} (English) of them don{'}t have a counterpart in their containing tweet{'}s translation. This analysis shows that 80{\%} of multiword hashtags are correctly translated by humans, and that the mistranslation of the rest may be due to incomplete translation directives regarding social media. We show how these resources and their analysis can guide the design of a machine translation pipeline, and its evaluation. A baseline system implementing a tweet-specific tokenizer yields promising results. The system is improved by translating epilogues, prologues, and text separately. We attempt to feed the SMT engine with the original hashtag and some alternatives ({``}dehashed{''} version or a segmented version of multiword hashtags), but translation quality improves at the cost of hashtag recall.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gotti-etal-2014-hashtag">
<titleInfo>
<title>Hashtag Occurrences, Layout and Translation: A Corpus-driven Analysis of Tweets Published by the Canadian Government</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabrizio</namePart>
<namePart type="family">Gotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atefeh</namePart>
<namePart type="family">Farzindar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an aligned bilingual corpus of 8758 tweet pairs in French and English, derived from Canadian government agencies. Hashtags appear in a tweet’s prologue, announcing its topic, or in the tweet’s text in lieu of traditional words, or in an epilogue. Hashtags are words prefixed with a pound sign in 80% of the cases. The rest is mostly multiword hashtags, for which we describe a segmentation algorithm. A manual analysis of the bilingual alignment of 5000 hashtags shows that 5% (French) to 18% (English) of them don’t have a counterpart in their containing tweet’s translation. This analysis shows that 80% of multiword hashtags are correctly translated by humans, and that the mistranslation of the rest may be due to incomplete translation directives regarding social media. We show how these resources and their analysis can guide the design of a machine translation pipeline, and its evaluation. A baseline system implementing a tweet-specific tokenizer yields promising results. The system is improved by translating epilogues, prologues, and text separately. We attempt to feed the SMT engine with the original hashtag and some alternatives (“dehashed” version or a segmented version of multiword hashtags), but translation quality improves at the cost of hashtag recall.</abstract>
<identifier type="citekey">gotti-etal-2014-hashtag</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/53_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2254</start>
<end>2261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hashtag Occurrences, Layout and Translation: A Corpus-driven Analysis of Tweets Published by the Canadian Government
%A Gotti, Fabrizio
%A Langlais, Phillippe
%A Farzindar, Atefeh
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F gotti-etal-2014-hashtag
%X We present an aligned bilingual corpus of 8758 tweet pairs in French and English, derived from Canadian government agencies. Hashtags appear in a tweet’s prologue, announcing its topic, or in the tweet’s text in lieu of traditional words, or in an epilogue. Hashtags are words prefixed with a pound sign in 80% of the cases. The rest is mostly multiword hashtags, for which we describe a segmentation algorithm. A manual analysis of the bilingual alignment of 5000 hashtags shows that 5% (French) to 18% (English) of them don’t have a counterpart in their containing tweet’s translation. This analysis shows that 80% of multiword hashtags are correctly translated by humans, and that the mistranslation of the rest may be due to incomplete translation directives regarding social media. We show how these resources and their analysis can guide the design of a machine translation pipeline, and its evaluation. A baseline system implementing a tweet-specific tokenizer yields promising results. The system is improved by translating epilogues, prologues, and text separately. We attempt to feed the SMT engine with the original hashtag and some alternatives (“dehashed” version or a segmented version of multiword hashtags), but translation quality improves at the cost of hashtag recall.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/53_Paper.pdf
%P 2254-2261
Markdown (Informal)
[Hashtag Occurrences, Layout and Translation: A Corpus-driven Analysis of Tweets Published by the Canadian Government](http://www.lrec-conf.org/proceedings/lrec2014/pdf/53_Paper.pdf) (Gotti et al., LREC 2014)
ACL