<HTML><HEAD></HEAD>
<BODY dir=ltr>
<DIV dir=ltr>
<DIV style="FONT-SIZE: 12pt; FONT-FAMILY: 'Calibri'; COLOR: #000000">
<DIV
style='FONT-SIZE: small; TEXT-DECORATION: none; FONT-FAMILY: "Calibri"; FONT-WEIGHT: normal; COLOR: #000000; FONT-STYLE: normal; DISPLAY: inline'>
<DIV dir=ltr>
<DIV style="FONT-SIZE: 12pt; FONT-FAMILY: 'Calibri'; COLOR: #000000">
<DIV> </DIV>
<DIV>
<DIV>***** Journal of Natural Language Engineering - Special Issue on “Machine
Translation Using Comparable Corpora” *****</DIV><BR>CALL FOR PAPERS</DIV>
<DIV> </DIV>
<DIV>Statistical machine translation based on parallel corpora has been very
successful. The major search engines' translation systems, which are used by
millions of people, are primarily using this approach, and it has been possible
to come up with new language pairs in a fraction of the time that would be
required when using more traditional rule-based methods.</DIV>
<DIV> </DIV>
<DIV>In contrast, research on comparable corpora is still at an earlier stage.
Comparable corpora can be defined as monolingual corpora covering roughly the
same subject area in different languages but without being exact translations of
each other.</DIV>
<DIV> </DIV>
<DIV>However, despite its tremendous success, the use of parallel corpora in MT
has a number of drawbacks:</DIV>
<DIV> </DIV>
<DIV>1) It has been shown that translated language is somewhat different from
original language, for example Klebanov & Flor showed that "associative
texture" is lost in translation. </DIV>
<DIV> </DIV>
<DIV>2) As they require translation, parallel corpora will always be a far
scarcer resource than comparable corpora. This is a severe drawback for a number
of reasons:</DIV>
<DIV> </DIV>
<DIV>a) Among the about 7000 world languages, of which 600 have a written form,
the vast majority are of the "low resource" type.</DIV>
<DIV> </DIV>
<DIV>b) The number of possible language pairs increases with the square of the
number of languages. When using parallel corpora, one bitext is needed for each
language pair. When using comparable corpora, one monolingual corpus per
language suffices.</DIV>
<DIV> </DIV>
<DIV>c) For improved translation quality, translation systems specialized on
particular genres and domains are desirable. But it is far more difficult to
acquire appropriate parallel rather than comparable training corpora.</DIV>
<DIV> </DIV>
<DIV>d) As language evolves over time, the training corpora should be updated on
a regular basis. Again, this is more difficult in the parallel case.</DIV>
<DIV> </DIV>
<DIV>For such reasons it would be a big step forward if it were possible to base
statistical machine translation on comparable rather than on parallel corpora:
The acquisition of training data would be far easier, and the unnatural
"translation bias" (source language shining through) within the training data
could be avoided.</DIV>
<DIV> </DIV>
<DIV>But is there any evidence that this is possible? Motivation for using
comparable corpora in MT research comes from a cognitive perspective: Experience
tells that persons who have learned a second language completely independently
from their mother tongue can nevertheless translate between the languages. That
is, human performance shows that there must be a way to bridge the gap between
languages which does not rely on parallel data. Using parallel data for MT is of
course a nice shortcut. But avoiding this shortcut by doing MT based on
comparable corpora may well be a key to a better understanding of human
translation, and to better MT quality.</DIV>
<DIV> </DIV>
<DIV>Work on comparable corpora in the context of MT has been ongoing for almost
20 years. It has turned out that this is a very hard problem to solve, but as it
is among the grand challenges in multilingual NLP, interest has steadily
increased. Apart from the increase in publications this can be seen from the
considerable number of research projects (such as ACCURAT and TTC) which are
fully or partially devoted to MT using comparable corpora. Given also the
success of the workshop series on “Building and Using Comparable Corpora“
(BUCC), which is now in its seventh year, and following the publication of a
related book (<A
href="http://www.springer.com/computer/ai/book/978-3-642-20127-1">http://www.springer.com/computer/ai/book/978-3-642-20127-1</A>),
we think that it is now time to devote a journal special issue to this field. It
is meant to bundle the latest top class research, make it available to everybody
working in the field, and at the same time give an overview on the state of the
art to all interested researchers.</DIV>
<DIV> </DIV>
<DIV><BR>TOPICS OF INTEREST</DIV>
<DIV> </DIV>
<DIV>We solicit contributions including but not limited to the following
topics:</DIV>
<DIV> </DIV>
<DIV>• Comparable corpora based MT systems (CCMTs)<BR>• Architectures for
CCMTs<BR>• CCMTs for less-resourced languages<BR>• CCMTs for less-resourced
domains<BR>• CCMTs dealing with morphologically rich languages<BR>• CCMTs for
spoken translation<BR>• Applications of CCMTs<BR>• CCMT evaluation<BR>• Open
source CCMT systems<BR>• Hybrid systems combining SMT and CCMT<BR>• Hybrid
systems combining rule-based MT and CCMT <BR>• Enhancing phrase-based SMT using
comparable corpora<BR>• Expanding phrase tables using comparable corpora<BR>•
Comparable corpora based processing tools/kits for MT<BR>• Methods for mining
comparable corpora from the Web<BR>• Applying Harris' distributional hypothesis
to comparable corpora<BR>• Induction of morphological, grammatical, and
translation rules from comparable corpora<BR>• Machine learning techniques using
comparable corpora<BR>• Parallel corpora vs. pairs of non-parallel monolingual
corpora<BR>• Extraction of parallel segments or paraphrases from comparable
corpora<BR>• Extraction of bilingual and multilingual translations of single
words and multi-word expressions, proper names, and named entities from
comparable corpora</DIV>
<DIV> </DIV>
<DIV><BR>IMPORTANT DATES<BR> <BR>December 1, 2014: Paper submission
deadline<BR>February 1, 2015: Notification<BR>May 1, 2015: Deadline for revised
papers<BR>July 1, 2015: Final notification<BR>September 1, 2015: Final paper
due</DIV>
<DIV> </DIV>
<DIV><BR>GUEST EDITORS</DIV>
<DIV> </DIV>
<DIV>Reinhard Rapp, Universities of Aix Marseille (France) and Mainz
(Germany)<BR>Serge Sharoff, University of Leeds (UK)<BR>Pierre Zweigenbaum,
LIMSI, CNRS (France)</DIV>
<DIV> </DIV>
<DIV><BR>FURTHER INFORMATION</DIV>
<DIV> </DIV>
<DIV>Please use the following e-mail address to contact the guest editors:
jnle.bucc (at) limsi (dot) fr</DIV>
<DIV> </DIV>
<DIV>Further details on paper submission will be made available in due course at
the BUCC website: <A
href="http://comparable.limsi.fr/bucc2014/bucc-introduction.html">http://comparable.limsi.fr/bucc2014/bucc-introduction.html</A></DIV>
<DIV> </DIV>
<DIV> </DIV></DIV></DIV></DIV></DIV></DIV></BODY></HTML>