<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content="text/html; charset=iso-8859-1" http-equiv=Content-Type>
<META name=GENERATOR content="MSHTML 8.00.6001.19170">
<STYLE></STYLE>
</HEAD>
<BODY bgColor=#ffffff>
<DIV><SPAN lang=DE>
<P>Apologies for multiple postings<BR>Please distribute to colleagues</P>
<P>======================================================================================</SPAN></P></DIV>
<DIV>Joint Workshop on<BR><BR>EXPLOITING SYNERGIES BETWEEN INFORMATION RETRIEVAL
AND MACHINE TRANSLATION (ESIRMT)<BR><BR>and<BR><BR>HYBRID APPROACHES TO MACHINE
TRANSLATION (HyTra)<BR><BR>Co-located with EACL 2012 (<A
href="http://eacl2012.org/" target=_blank>http://eacl2012.org/</A>)<BR>Avignon,
France<BR>April 23 and 24, 2012<BR><BR>Deadline for paper submissions: February
2, 2012<BR><BR><A href="http://www-lium.univ-lemans.fr/esirmt-hytra"
target=_blank>http://www-lium.univ-lemans.fr/esirmt-hytra</A><BR><BR>======================================================================================<BR><BR><BR>This
two-day workshop addresses two specific but related research problems in
computational<BR>linguistics.<BR><BR>The ESIRMT event (1st day) aims at reducing
the gap, both theoretical and practical, between<BR>information retrieval and
machine translation research and applications. Although both fields have<BR>been
already contributing to each other instrumentally, there is still too much work
to be done in<BR>relation to solidly framing these two fields into a common
ground of knowledge from both the<BR>procedural and paradigmatic
perspectives.<BR><BR>The HyTra event (2nd day) aims at sharing ideas among
researchers developing and applying<BR>statistical, example-based, or rule-based
machine translation systems and who wish to enhance their<BR>systems with
elements from the other approaches.<BR><BR>The joint workshop will provide
participants with the opportunity of discussing research related
to<BR>technology integration and system combination strategies at both the
general level of cross-language<BR>information access and the specific level of
machine translation technologies.<BR><BR>Contributions are to be organized into
two tracks, corresponding to ESIRMT and HyTra, respectively.<BR>Topics of
interest include, but are not limited to:<BR><BR>ESIRMT track:<BR><BR>* machine
translation and information retrieval hybridization<BR>* applications of MT and
IR hybrid systems<BR>* IR techniques integrated in MT systems<BR>* MT techniques
integrated in IR systems<BR>* any kind of innovative approach exploiting
synergies between MT and IR<BR>* machine learning techniques for
ranking<BR><BR>HyTra track:<BR><BR>* ways and techniques of MT
hybridization<BR>* architectures for the rapid development of hybrid MT
systems<BR>* hybrid systems dealing with underresourced languages and/or with
morphologically rich languages<BR>* using linguistic information (morphology,
syntax, semantics) to enhance statistical MT<BR>* bootstrapping rule-based
systems from corpora<BR>* hybrid methods in spoken language translation<BR>*
extraction of dictionaries from parallel and comparable corpora<BR>* machine
learning techniques for hybrid MT<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>* system combination approaches<BR>* open
source tools and free language resources for hybrid MT<BR><BR><BR>SUBMISSION
INSTRUCTIONS<BR><BR>Authors are invited to submit papers on original and
previously unpublished work. Formatting should<BR>be according to EACL
2012 specifications using LaTeX or MS-Word style files, see<BR><A
href="http://eacl2012.org/information-for-authors/index.html"
target=_blank>http://eacl2012.org/information-for-authors/index.html</A> (paper
length: up to 9 pages plus an extra<BR>page for references). Reviewing of papers
will be double-blind, so the submissions should not reveal<BR>the authors'
identity.<BR><BR>Submission is electronic in PDF format using the START
submission system at<BR><BR><A
href="https://www.softconf.com/eacl2012/ESIRMT-HyTra/"
target=_blank>https://www.softconf.com/eacl2012/ESIRMT-HyTra/</A><BR><BR>Double
submission policy: Parallel submission to other meetings or publications are
possible but<BR>must be immediately notified to the workshop contact person (see
below).<BR><BR>Authors of accepted papers will be invited to present their
research at the workshop. The papers<BR>will be published in the
electronic workshop proceedings. These will be part of the EACL<BR>proceedings,
published by ACL. They will also be made available online via the ACL
Anthology.<BR><BR><BR>IMPORTANT DATES<BR><BR>February 2, 2012: Paper
submissions due<BR>February 24, 2012: Notification of acceptance<BR>March
9, 2012: Camera ready papers due<BR>April 23-24, 2012: Workshop in
Avignon<BR><BR><BR>ORGANIZERS<BR><BR>Contact person: Marta R. Costa-jussà
(e-mail: <A href="mailto:marta.ruiz@barcelonamedia.org"
target=_blank>marta.ruiz@barcelonamedia.org</A> )<BR><BR>ESIRMT: Marta R.
Costa-jussà (Barcelona Media Innovation Center), Patrik Lambert (University of
Le<BR>Mans), Rafael E. Banchs (Institute for Infocomm Research)<BR><BR>HyTra:
Reinhard Rapp (Universities of Mainz and Leeds), Bogdan Babych (University of
Leeds), Kurt<BR>Eberle (Lingenio GmbH), Tony Hartley (Toyohashi University of
Technology and University of Leeds),<BR>Serge Sharoff (University of Leeds),
Martin Thomas (University of Leeds)<BR><BR><BR>INVITED SPEAKERS<BR><BR>Philipp
Koehn (University of Edinburgh)<BR>Christof Monz (University of
Amsterdam)<BR><BR><BR>PROGRAMME COMMITTEE<BR><BR>Jordi Atserias, Yahoo! Research
, Barcelona, Spain<BR>Bogdan Babych, University of Leeds, UK<BR>Sivaji
Bandyopadhyay, Jadavpur University, Kolkata, India<BR>Núria Bel, Universitat
Pompeu Fabra, Barcelona, Spain<BR>Pierrette Bouillon, ISSCO/TIM/ETI, University
of Geneva, Switzerland<BR>Chris Callison-Burch, Johns Hopkins University,
Baltimore, USA<BR>Michael Carl, Copenhagen Business School, Denmark<BR>Oliver
Culo, ICSI, University of California, Berkeley, USA<BR>Kurt Eberle, Lingenio
GmbH, Heidelberg, Germany<BR>Andreas Eisele, Directorate-General for
Translation, European Commission, Luxembourg<BR>Marcello Federico, Fondazione
Bruno Kessler, Trento, Italy<BR>José A. R. Fonollosa, Universitat Politècnica de
Catalunya, Barcelona, Spain<BR>Mikel Forcada, University of Alicante,
Spain<BR>Alexander Fraser, Institute for Natural Language Processing (IMS),
Stuttgart, Germany<BR>Johanna Geiß, Lingenio GmbH, Heidelberg, Germany<BR>Mireia
Ginesti-Rosell, Lingenio GmbH, Heidelberg, Germany<BR>Silvia Hansen-Schirra,
FTSK, University of Mainz, Germany<BR>Tony Hartley, Toyohashi University of
Technology, Japan, and University of Leeds, England<BR>Gareth Jones, Dublin City
University, Ireland<BR>Min-Yen Kan, National University of Singapore<BR>Udo
Kruschwitz, University of Essez, UK<BR>Yanjun Ma, Baidu Inc. Beijing,
China<BR>José B. Mariño, Universitat Politècnica de Catalunya, Spain<BR>Maite
Melero, Barcelona Media Innovation Center, Barcelona, Spain<BR>Haizhou Li,
Institute for Infocomm Research, Singapore<BR>Reinhard Rapp, University of
Mainz, Germany, and University of Leeds, UK<BR>Paul Schmidt, Institut for
Applied Information Science, Saarbrücken, Germany<BR>Uta Seewald-Heeg, Anhalt
University of Applied Sciences, Köthen, Germany<BR>Nasredine Semmar, CEA LIST,
France<BR>Serge Sharoff, University of Leeds, UK<BR>Wade Shen, Massachusetts
Institute of Technology, Cambridge, USA<BR>Fabrizio Silvestri, Instituto de
Scienza e Tecnologia del'Informazione, Pisa, Italy<BR>Harold Somers, CNGL,
Dublin City University, Ireland<BR>Anders Søgaard, University of Copenhagen,
Denmark<BR>Martin Thomas, University of Leeds, UK<BR>Jörg Tiedemann, University
of Uppsala, Sweden<BR>Zygmunt Vetulani, University of Poznan,
Poland<BR><BR></DIV></BODY></HTML>