<div dir="ltr"><br><div class="gmail_quote"><div dir="ltr"><div>
<p style="text-align:justify"><i><a href="http://www.journals.elsevier.com/computer-speech-and-language/call-for-papers/special-issue-on-deep-learning-for-machine-translation/" target="_blank">Computer Speech andLanguage Special Issue on Deep Learning for Machine Translation </a></i></p>
<p style="text-align:justify"><i> </i></p>
<p style="text-align:justify">Deep Learning has been
successfully applied to many areas including Natural Language Processing,
Speech Recognition and Image Processing. Deep learning techniques have
surprised the entire community both academy and industry by powerfully learning
from data.</p>
<p style="text-align:justify"> </p><p style="text-align:justify">Recently, deep learning has
been introduced to Machine Translation (MT). It first started as a kind of
feature which was integrated in standard phrase or syntax-based statistical
approaches. Deep learning has been shown useful in translation and language
modeling as well as in reordering, tuning and rescoring. Additionally, deep
learning has been applied to MT evaluation and quality estimation.</p><p style="text-align:justify"></p>
<p style="text-align:justify"> </p>
<p style="text-align:justify">But the biggest impact on MT
appeared with the new paradigm proposal: Neural MT, which has just recently (in
the Workshop of Machine Translation 2015) outperformed state-of-the-art
systems. This new approach uses an autoencoder architecture to build a neural
system that is capable of translating. With the new approach, the new big MT
challenges lie on how to deal with large vocabularies, document translation and
computational power among others<u>.</u></p>
<p style="text-align:justify"> </p>
<p style="text-align:justify">This hot topic is raising
interest from the scientific community and as a response there have been
several related events (i.e. tutorial<a href="#151a106fdef5395b__ftn1" name="151a106fdef5395b__ftnref1" title=""><span><span><span style="font-size:10pt;line-height:115%;font-family:'Times New Roman'">[1]</span></span></span></a>
and winter school<a href="#151a106fdef5395b__ftn2" name="151a106fdef5395b__ftnref2" title=""><span><span><span style="font-size:10pt;line-height:115%;font-family:'Times New Roman'">[2]</span></span></span></a>).
Moreover, the number of publications on this topic in top conferences such as
ACL, NAACL, EMNLP has dramatically increased in the last three years. This
would be the first special issue related to the topic. With this special issue,
we pretend to offer a compilation of works that give the reader a global vision
of how the deep learning techniques are applied to MT and what new challenges
offers. </p>
<p style="text-align:justify"> </p>
<p style="text-align:justify">This Special Issue expects
high quality submissions on the following topics (but not limited): </p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>Including deep learning knowledge in standard MT
approaches (statistical, rule-based, example-based...) </p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>Neural MT approaches </p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>MT hybrid techniques using deep learning</p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>Deep learning challenges in MT: vocabulary
limitation, document translation, computational power</p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>MT evaluation with deep learning techniques</p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>MT quality estimation with deep learning
techniques</p>
<p style="margin-left:36pt;text-align:justify"><span style="font-family:Symbol">·<span style="font-size:7pt;line-height:normal;font-family:'Times New Roman'"> </span></span>Using deep learning in spoken language
translation </p>
<p style="text-align:justify"> </p>
<p style="text-align:justify">*IMPORTANT DATES*</p>
<p style="text-align:justify">Submission deadline: 30th
March 2016 </p>
<p style="text-align:justify">Notification of
rejection/re-submission: 30th July 2016</p>
<p style="text-align:justify">Notification of final acceptance:
30th October 2016</p>
<p style="text-align:justify">Expected publication date: 30th
January 2017</p>
<div><br></div><div><br></div>*GUEST EDITORS*<br><br>Marta R. Costa-jussà, Universitat Politècnica de Catalunya, Spain. <a href="mailto:marta.ruiz@upc.edu" target="_blank">marta.ruiz@upc.edu</a><br><br>Alexandre Allauzen, Centre National de la Recherche Scientifique, France. <a href="mailto:allauzen@limsi.fr" target="_blank">allauzen@limsi.fr</a><br><br>Loïc Barrault, Université du Maine, France. <a href="mailto:loic.barrault@lium.univ-lemans.fr" target="_blank">loic.barrault@lium.univ-lemans.fr</a><br><br>Kyunghyun Cho, New York University, USA. <a href="mailto:kyunghyun.cho@nyu.edu" target="_blank">kyunghyun.cho@nyu.edu</a><br><br>Holger Schwenk, Facebook, USA. <a href="mailto:schwenk@fb.com" target="_blank">schwenk@fb.com</a><br><br><div><br></div><div><br clear="all">
<hr align="left" size="1" width="33%">
<div>
<p><a href="#151a106fdef5395b__ftnref1" name="151a106fdef5395b__ftn1" title=""><span><span><span style="font-size:10pt;line-height:115%;font-family:'Times New Roman'">[1]</span></span></span></a> <a href="http://naacl.org/naacl-hlt-2015/tutorial-deep-learning.html" target="_blank">http://naacl.org/naacl-hlt-2015/tutorial-deep-learning.html</a></p>
</div>
<div>
<p><a href="#151a106fdef5395b__ftnref2" name="151a106fdef5395b__ftn2" title=""><span><span><span style="font-size:10pt;line-height:115%;font-family:'Times New Roman'">[2]</span></span></span></a> <a href="http://dl4mt.computing.dcu.ie/" target="_blank">http://dl4mt.computing.dcu.ie/</a></p>
</div>
</div>
</div><div><div dir="ltr"><div><br></div></div></div>
</div>
</div><br><br>
</div>