<div dir="ltr">============================================================<br>TWEETLID 2014<br>Workshop on Tweet Language Identification<br>co-located with the XXX Conference of the Spanish Society for Natural Language Processing, SEPLN 2014<br>
Girona, Spain<br><br>September 16, 2014<br><a href="http://komunitatea.elhuyar.org/tweetlid/">http://komunitatea.elhuyar.org/tweetlid/</a><br>============================================================<br><br>------------------------------------------------------------<br>
CALL FOR PAPERS<br>------------------------------------------------------------<br><br>TweetLID
2014 invites researchers to submit novel and unpublished work on the
identification of the language or languages in which a tweet is written.
We have organized a shared task for this purpose, where we will provide
participants with a suitable corpus and evaluation methodology to
pursue the development of such research.<br><br>Introduction<br>------------<br><br>TweetLID
is a workshop and shared task on the automatic identification of the
language in which tweets are written. It will take place on September
16, 2014, in Girona, co-located with SEPLN 2014. The objective of the
task is to bring together researchers interested in the topic, as well
as to join forces to experiment with and compare different approaches
for identification of tweet languages.<br><br>The identification of
tweet language is arousing an increasing interest in the scientific
community (Carter et al., 2013). Identifying the language in which a
tweet is written is crucial if we intend to apply NLP techniques
subsequently on the tweet, e.g., machine translation, sentiment
analysis, information extraction, etc. Accurately identifying the
language will facilitate the application of resources suitable to the
language in question.<br><br>However, despite the increasing volume of
research in identification of major languages such as English, French,
or Spanish, the application of these techniques to other languages with
lesser presence on Twitter has not been studied in detail. The scope of
the task will focus on the 5 top languages of the Iberian Peninsula
(Spanish, Portuguese, Catalan, Basque, and Galician), besides English.
These languages are likely to co-occur along with many news and events
relevant to the Iberian Peninsula, and thus an accurate identification
of the language is key to make sure that we use the appropriate
resources for the linguistic processing.<br><br>The workshop aims to be a
forum where researchers will have a chance to compare their algorithms,
systems, and results. The organizing committee will release an
annotated development corpus that will enable participants to train
their systems. The final evaluation will be conducted with another
unannotated corpus that the participants will have to submit with their
results in a short period of time.<br><br>Corpus<br>------<br><br>The
corpus that we will provide to participants of the shared task includes
geolocated tweets posted from different regions of the Iberian
Peninsula, with a strong focus on bilingual areas. We have built a
corpus of tweets annotated with the language(s) they are written in. We
will split this corpus into a training set, which will be shared with
participants in the first stage, and into another test set, which will
be released in the evaluation stage. The participants will have to
develop their systems to identify the language(s) of the tweets in the
test set, and submit their responses. Each participant will be allowed
to submit the responses of up to two systems.<br><br>Registration<br>------------<br><br>Interested
participants need to register for the task and workshop by sending an
email to <a href="mailto:tweetlid@elhuyar.com">tweetlid@elhuyar.com</a> on or before May 30th.<br><br>Paper submission<br>----------------<br><br>Submissions
will not exceed the maximum length of 4 pages, and will be formatted
following the SEPLN journal styles
(<a href="http://www.sepln.org/home-2/revista/instrucciones-autor/">http://www.sepln.org/home-2/revista/instrucciones-autor/</a>).<br><br>The proceedings of the workshop will be published using the <a href="http://ceur-ws.org">ceur-ws.org</a> repository, and will be indexed by DBLP.<br>
<br>Important dates<br>---------------<br><br>* June 6th: Inscription deadline <br>* June 2nd: Release of the development-set<br>* July 1st: Release of the test-set<br>* July 3rd: Result submission deadline<br>* July 12th: Result publication<br>
* July 25th: Short paper submission deadline<br>* August 31st: Papers' camera ready version<br>* September 16th: Workshop<br clear="all"><br>-- <br><div dir="ltr"><br><table cellpadding="0" border="0" height="40" width="329">
<tbody><tr><td><p><font style="font-family:Helvetica,Arial,sans-serif"><font size="1"><b>Iñaki San Vicente Roncal</b> </font><br>
<font color="#666666" size="1">I+G<font size="1"> <font size="1">I<font size="1">KERTZAILEA / R&D RE<font size="1">SEARCHER</font><br></font></font></font></font></font></p></td>
</tr></tbody></table><table><tbody>
</tbody></table>
<img src="http://www.elhuyar.org/irudiak/logoak/elh-hizkuntza.png" height="39" width="96"> <img src="http://komunitatea.elhuyar.org/imgTN/log_IXA.png" height="42" width="96">
<font style="font-family:Helvetica,Arial,sans-serif" color="#666666">
<p><font><font size="1"><a href="mailto:i.sanvicente@elhuyar.com" style="color:rgb(102,102,102);text-decoration:none" target="_blank">i.sanvicente@elhuyar.com | </a></font></font><font><font size="1"><a href="mailto:i.sanvicente@elhuyar.com" style="color:rgb(102,102,102);text-decoration:none" target="_blank"><font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><font><font size="1"></font></font></font></a><font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><font><font size="1"><a href="mailto:inaki.sanvicente@ehu.es" style="color:rgb(102,102,102);text-decoration:none" target="_blank">inaki.sanvicente@ehu.es</a></font></font></font></font> <font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><font style="font-family:Helvetica,Arial,sans-serif" color="#666666">|</font> </font> </font><font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><font><a href="http://scholar.google.es/citations?user=eb_xVO4AAAAJ&hl=en" target="_blank"><img src="http://i1.itools.com/i/fav/google-scholar-published-research.png"></a></font></font><font> <a href="https://www.researchgate.net/profile/Inaki_San_Vicente/" target="_blank"><font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><img src="http://www.fernando.parreiras.nom.br/images/researchgate.png" height="17" width="17"></font></a><br>
</font>
<font size="1">tel. Elhuyar: 943363040 | luzp.: 225</font><br><font style="font-family:Helvetica,Arial,sans-serif" color="#666666"><font size="1">tel. Ixa: 943015110 | 314 bulegoa<br></font></font></p><font size="1">
</font><p><font size="1"> Zelai Haundi, 3. Osinalde industrialdea</font><br><font size="1">
20170 Usurbil</font></p>
</font>
<p><font style="font-family:Helvetica,Arial,sans-serif" color="#3a75c4" size="1"><a href="http://www.elhuyar.org" style="color:rgb(58,117,196);text-decoration:none" target="_blank"><b>www.elhuyar.org</b></a><b> | </b><a href="http://ixa.si.ehu.es" style="color:rgb(58,117,196);text-decoration:none" target="_blank"><b>ixa.si.ehu.es </b></a></font></p>
<font style="font-family:Helvetica,Arial,sans-serif" color="gray" size="1">
</font><p style="margin-bottom:0cm"><font size="1"><span style="font-family:times new roman,serif"><font color="#808080" size="1">Mezu
honek, baita erantsitako edozein agirik ere, isilpeko informazioa
izan dezake. Informazio hori jasotzeko baimena izendatutakoak baino
ez du. Zu ez bazara adierazitako hartzailea, indarrean dagoen
legeriaren arabera debekatuta daukazu informazio hori baimenik gabe
erabili, hedatu eta/edo<font size="1"> </font>kopiatzea. Mezu hau errakuntza baten ondorioz
jaso baduzu, jakinarazi bidaltzaileari, eta ezaba ezazu. Eskerrik
asko.</font></span></font></p><table cellpadding="2" cellspacing="0" height="38" width="369"><tbody><tr><td style="border:medium none;padding:0cm" width="39"><br></td><td style="border:medium none;padding:0cm" width="202">
<p style="text-align:left"><font color="#008000" size="1"><font face="Helvetica, Arial, sans-serif">Ez
inprimatu mezu hau ezinbestekoa ez bada. </font></font>
</p>
</td>
</tr>
</tbody></table><span style="font-size:8pt;font-family:Tahoma;color:green" lang="EU"></span></div>
</div>