[Corpora-List] CFP: HLT-NAACL 2006 Workshop on Statistical Machine Translation

Christof Monz christof at dcs.qmul.ac.uk
Thu Dec 8 19:51:01 CET 2005

First Call for Papers


June 8 or June 9, 2006


Translating documents from foreign languages into English (or between
any two languages) by computer is one of the oldest goals in
computational linguistics. Now, armed with vast amounts of digitally
available translated text and powerful computers, we are witnessing
significant progress toward achieving that goal. Statistical methods
allow the analysis of parallel text corpora and the automatic
construction of machine translation systems. Already, for some
language pairs such as Chinese-English or Arabic-English, statistical
machine translation (SMT) systems built at research labs outperform
commercial systems.

The focus of this workshop is to use parallel corpora for machine
translation. It can be seen as an attempt to repeat the success of the
2005 ACL Workshop on Parallel Text, organized last year, which
featured a track on statistical machine translation and a shared task
on building machine translation systems.

Recent experimentation has shown that the performance of SMT systems
varies greatly with the source and target language. In this workshop
we would like to encourage researchers to investigate ways to improve
the performance of SMT systems for diverse languages, including
morphologically complex languages (e.g., Finnish) and languages with
partial free word order (e.g., German). Besides experimental work and
system building, we also encourage linguistic analysis of problems of
the current state of the art in statistical machine translation, as
showcased by last year's ACL 2005 Workshop on Parallel Text shared

Topics of interest include, but are not limited to:

* word-based, chunk-based, phrase-based, syntax-based SMT
* using comparable corpora for SMT
* using morphological and POS information for SMT
* integration of rule-based MT and statistical MT
* decoding
* error analysis
* Statistical MT for resource-poor languages
* Domain robustness/adaptation for MT
* Evaluation of translation quality


In addition to submissions on the topics listed above, this workshop
features a shared task and we encourage participants to evaluate their
approaches on that task. The shared task is to evaluate your approach
to machine translation---see the list of topics of interests
above---on the Europarl corpus.

We provide training data for three European language pairs, and a
common framework (including a language model and a baseline
system). The task is to improve methods to build a phrase translation
table (e.g. by better word alignment, phrase extraction, phrase
scoring), augment the system otherwise (e.g. by preprocessing), or
build entirely new translation systems.

The participants' system is used to translate a test set of unseen
sentences in the source language. The translation quality is measured
by the BLEU score, which measures overlap with a reference
translation, and manual evaluation. Participants agree to contribute
to the manual evaluation about eight hours of work.

To have a common framework that allows for comparable results, and
also to lower the barrier to entry, we provide

* a fixed training set
* a fixed language model
* a fixed baseline system

More information on the shared task can be found at:


Submissions will consist of regular full papers of max. 8 pages,
formatted following the NAACL 2006 guidelines. Authors of regular full
papers will be required to indicate a track for their submission. In
addition, teams participating in the shared tasks will be invited to
submit short papers (max. 4 pages) describing their systems. Both
submission and review processes will be handled electronically.


Regular papers:

Submissions: March 17
Notification: April 7
Shared Task:

Results submissions: March 31
Short paper submissions: April 7
Notification: April 14

Camera-ready papers April 21



Philipp Koehn (University of Edinburgh)
Christof Monz (Queen Mary, University of London)


For questions, comments, etc. please send email to
naacl.wmt06 at dcs.qmul.ac.uk


Bill Byrne (University of Cambridge)
Chris Callison-Burch (University of Edinburgh)
Francisco Casacuberta (University of Valencia)
David Chiang (University of Maryland)
Stephen Clark (Oxford University)
Marcello Federico (ITC-IRST)
George Foster (Canada National Research Council)
Alexander Fraser (ISI/University of Southern California)
Jan Hajic (Charles University)
Kevin Knight (ISI/University of Southern California)
Greg Kondrak (University of Alberta)
Shankar Kumar (Google)
Philippe Langlais (University of Montreal)
Daniel Marcu (ISI/University of Southern California)
Dan Melamed (New York University)
Franz-Josef Och (Google)
Miles Osborne (University of Edinburgh)
Philip Resnik (University of Maryland)
Libin Shen (University of Pennsylvania)
Wade Shen (MIT-Lincoln Labs)
Michel Simard (Canada National Research Council)
Eiichiro Sumita (ATR Spoken Language Translation Research Laboratories)
Joerg Tiedemann (University of Groningen)
Christoph Tillmann (IBM)
Taro Watanabe (ATR Spoken Language Translation Research Laboratories)
Richard Zens (RWTH Aachen)

More information about the Corpora-archive mailing list