<HTML><HEAD></HEAD>
<BODY dir=ltr>
<DIV dir=ltr>
<DIV style="FONT-SIZE: 12pt; FONT-FAMILY: 'Calibri'; COLOR: #000000">
<DIV>
<DIV
style='FONT-SIZE: small; TEXT-DECORATION: none; FONT-FAMILY: "Calibri"; FONT-WEIGHT: normal; COLOR: #000000; FONT-STYLE: normal; DISPLAY: inline'></DIV></DIV>
<DIV>
<DIV
style='FONT-SIZE: small; TEXT-DECORATION: none; FONT-FAMILY: "Calibri"; FONT-WEIGHT: normal; COLOR: #000000; FONT-STYLE: normal; DISPLAY: inline'>***
DEADLINE EXTENSION TO FEBRUARY 7, 2014 ***</DIV>
<DIV dir=ltr>
<DIV style="FONT-SIZE: 12pt; FONT-FAMILY: 'Calibri'; COLOR: #000000">
<DIV> </DIV>
<DIV>=================================================================</DIV>
<DIV> </DIV>
<DIV>THIRD WORKSHOP ON HYBRID APPROACHES TO TRANSLATION (HyTra 2014)</DIV>
<DIV> </DIV>
<DIV>Co-located with EACL 2014 <A
href="http://eacl2014.org/">http://eacl2014.org/</A> </DIV>
<DIV> </DIV>
<DIV>Gothenburg, Sweden</DIV>
<DIV> </DIV>
<DIV>April 27, 2014</DIV>
<DIV> </DIV>
<DIV><A
href="http://www.upf.edu/glicom/hytra2014.html">http://www.upf.edu/glicom/hytra2014.html</A></DIV>
<DIV> </DIV>
<DIV><BR>INVITED SPEAKERS</DIV>
<DIV> </DIV>
<DIV>Hans Uszkoreit (Saarland University and DFKI, Germany)<BR>Joakim Nivre
(Uppsala University,
Sweden)
</DIV>
<DIV> </DIV>
<DIV>=================================================================</DIV>
<DIV> </DIV>
<DIV><BR>WORKSHOP DESCRIPTION</DIV>
<DIV> </DIV>
<DIV>The aim of the HyTra workshop series is to bring together researchers
developing and applying statistical, example-based, or rule-based translation
systems, and those enhancing MT systems by combining elements from different
approaches, to promote discussion and sharing of ideas among them. Hereby one
relevant focus is on effectively combining linguistic and data driven approaches
(rule-based and statistical MT). Another focus is on hybridization in the
context of human translation.</DIV>
<DIV> </DIV>
<DIV>The 3rd Workshop on Hybrid Approaches to Translation (HyTra-3) intends to
continue developing and empowering the research agenda in the area of Hybrid
Translation already started at its first and second editions. The previous two
editions (see <A
href="http://www-lium.univ-lemans.fr/esirmt-hytra/">http://www-lium.univ-lemans.fr/esirmt-hytra/</A>
and <A
href="http://hytra.barcelonamedia.org/hytra2013/">http://hytra.barcelonamedia.org/hytra2013/</A>)
were co-located with EACL 2012 in Avignon and with ACL 2013 in Sofia, and the
proceedings were published on the ACL Anthology.</DIV>
<DIV> </DIV>
<DIV><BR>TOPICS</DIV>
<DIV> </DIV>
<DIV>We solicit contributions including but not limited to the following
topics:</DIV>
<DIV> </DIV>
<DIV>- ways and techniques of hybridization<BR>- architectures for the rapid
development of hybrid MT systems<BR>- applications of hybrid systems<BR>- hybrid
systems dealing with under-resourced languages<BR>- hybrid systems dealing with
morphologically rich languages<BR>- using linguistic information (morphology,
syntax, semantics) to enhance statistical MT <BR> (e.g. with hierarchical
or factored models)<BR>- using contextual information to enhance statistical
MT<BR>- bootstrapping rule-based systems from corpora<BR>- hybrid methods in
spoken language translation<BR>- extraction of dictionaries and other
large-scale resources for MT from parallel and comparable corpora<BR>- induction
of morphological, grammatical, and translation rules from corpora<BR>- machine
learning techniques for hybrid MT<BR>- describing structural mappings between
languages (e.g. tree-structures using <BR> synchronous/transduction
grammars)<BR>- heuristics for limiting the search space in hybrid MT<BR>-
alternative methods for the fair evaluation of the output of different types of
MT systems <BR> (e.g. relying on linguistic criteria)<BR>- system
combination approaches such as multi-engine MT (parallel) or automatic
post-editing (sequential)<BR>- open source tools and free language resources for
hybrid MT</DIV>
<DIV> </DIV>
<DIV><BR>SUBMISSIONS</DIV>
<DIV> </DIV>
<DIV>Contributions can be short or long papers. Short paper submissions must
describe original and unpublished work without exceeding five pages of content
plus one extra page for references. Characteristics of short papers include: a
small, focused contribution; work in progress; a negative result; an opinion
piece; an interesting application nugget. Long paper submissions must describe
substantial, original, completed and unpublished work without exceeding eight
pages of content plus two extra pages for references. Submissions will be judged
according to the criteria of the main conference (EACL 2014).</DIV>
<DIV> </DIV>
<DIV>Authors are invited to submit papers on original and previously unpublished
work. Formatting should be according to EACL 2014 specifications using LaTeX or
MS-Word style files, see section "submission format" at <A
href="http://eacl2014.org/call-for-papers">http://eacl2014.org/call-for-papers</A>.
Reviewing of papers will be double-blind, so the submissions should not reveal
the authors' identity.</DIV>
<DIV> </DIV>
<DIV>Submission is electronic in PDF format using the START submission system at
the following URL: <A
href="https://www.softconf.com/eacl2014/HyTra/">https://www.softconf.com/eacl2014/HyTra/</A>
</DIV>
<DIV> </DIV>
<DIV>Double submission policy: Parallel submission to other meetings or
publications is possible but must be immediately notified to the workshop
contact person (see below). If accepted, withdrawals are only possible within
two days after notification.</DIV>
<DIV> </DIV>
<DIV>For an accepted paper to appear in the proceedings, at least one author
must register for the workshop and actually present the paper. The papers will
be published in the workshop proceedings which will be made available via the
ACL Anthology.</DIV>
<DIV> </DIV>
<DIV><BR>BEST PAPERS</DIV>
<DIV> </DIV>
<DIV>Authors of selected papers will be invited to contribute extended versions
of their papers as book chapters for an edited volume on hybrid MT.</DIV>
<DIV> </DIV>
<DIV><BR>IMPORTANT DATES</DIV>
<DIV> </DIV>
<DIV>February 7, 2014: Extended deadline for paper submission<BR>February 20,
2014: Notification of acceptance<BR>March 3, 2014: Camera ready papers
due<BR>April 27, 2014: Workshop in Gothenburg</DIV>
<DIV> </DIV>
<DIV><BR>ORGANIZERS</DIV>
<DIV> </DIV>
<DIV>Rafael E. Banchs (Institute for Infocomm Research, Singapore)<BR>Marta R.
Costa-jussa (Institute for Infocomm Research, Singapore)<BR>Reinhard Rapp
(Universities of Aix-Marseille and Mainz)<BR>Patrik Lambert (Pompeu Fabra
University, Barcelona)<BR>Kurt Eberle (Lingenio GmbH, Heidelberg)<BR>Bogdan
Babych (University of Leeds)</DIV>
<DIV> </DIV>
<DIV><BR>CONTACT PERSON</DIV>
<DIV> </DIV>
<DIV>Rafael E. Banchs: rembanchs (at) i2r (dot) a-star (dot) edu (dot) sg</DIV>
<DIV> </DIV>
<DIV><BR>PROGRAMME COMMITTEE</DIV>
<DIV> </DIV>
<DIV>* Ahmet Aker, University of Sheffield, UK<BR>* Bogdan Babych, University of
Leeds, UK<BR>* Rafael E. Banchs, Institute for Infocomm Research, Singapore<BR>*
Alexey Baytin, Yandex, Moscow, Russia <BR>* Núria Bel, Universitat Pompeu Fabra,
Barcelona, Spain <BR>* Pierrette Bouillon, ISSCO/TIM/ETI, University of Geneva,
Switzerland <BR>* Michael Carl, Copenhagen Business School, Denmark<BR>* Marta
R. Costa-jussa, Institute for Infocomm Research, Singapore<BR>* Oliver Culo,
University of Mainz, Germany<BR>* Kurt Eberle, Lingenio GmbH, Heidelberg,
Germany<BR>* Andreas Eisele, DGT (European Commission), Luxembourg <BR>*
Marcello Federico, Fondazione Bruno Kessler, Trento, Italy <BR>* Christian
Federmann, Language Technology Lab, DFKI, Saarbrücken, Germany <BR>* José A. R.
Fonollosa, Universitat Politècnica de Catalunya, Barcelona, Spain <BR>* Maxim
Khalilov, TAUS, Amsterdam, The Netherlands<BR>* Patrik Lambert, Pompeu Fabra
University, Barcelona, Spain<BR>* Udo Kruschwitz, University of Essex, UK <BR>*
Yanjun Ma, Baidu Inc., Beijing, China <BR>* José B. Mariño, Universitat
Politècnica de Catalunya, Barcelona, Spain <BR>* Bart Mellebeek, University of
Amsterdam, The Netherlands<BR>* Hermann Ney, RWTH Aachen, Germany<BR>* Reinhard
Rapp, Universities of Aix-Marseille, France, and Mainz, Germany<BR>* Anders
Søgaard, University of Copenhagen, Denmark <BR>* Nasredine Semmar, CEA LIST,
Fontenay-aux-Roses, France <BR>* Wade Shen, Massachusetts Institute of
Technology, Cambridge, USA <BR>* Serge Sharoff, University of Leeds, UK <BR>*
George Tambouratzis, Institute for Language and Speech Processing, Athens,
Greece<BR>* Jörg Tiedemann, University of Uppsala, Sweden <BR>* Dekai Wu, The
Hong Kong University of Science and Technology, Hong Kong, China
<BR> </DIV></DIV></DIV></DIV></DIV></DIV></BODY></HTML>