[Corpora-List] First CFP: Second International Workshop on Free/Open-Source Rule-based Machine Translation

Felipe Sánchez Martínez fsanchez at dlsi.ua.es
Tue Sep 21 15:04:42 UTC 2010


[Apologies for cross-posting]

***********************  First Call for Papers  ************************

Second International Workshop on Free/Open-Source Rule-based Machine 
Translation

20th--21st January 2011  - Barcelona, Spain

http://www.uoc.edu/freerbmt11/

Important dates:

* 8th November  -  Submission deadline
* 22nd November  -  Notification to authors
* 6th December  -  Deadline for camera-ready copy
* 20th-21st January  -  Workshop

Description:

The free/open-source development model has been adopted by many machine 
translation (MT) researchers and developers who are opening their code 
to the community. This benefits, on the one hand, machine translation 
users who have access to machine translation software that they can 
adapt to suit their needs, and, on the other hand, to machine 
translation researchers and developers who get valuable feedback to 
improve their systems.

Machine translation systems mainly depend on both algorithms 
(translation engines) and data (linguistic rules, parallel corpora, 
etc.). Hence, not only the implementation of the algorithms must be 
free/open-source, but also the data themselves. Nowadays, there are many 
machine translation packages of this type available, but most of them 
are corpus-based, and, in particular, statistical machine translation 
systems (SMT): rule-based (RBMT) systems built on these principles are 
still not so widely known. Both SMT and RBMT paradigms have benefits and 
drawbacks and none of them can be identified as inherently better than 
the other; in fact, hybridisation is currently an active field of research.

An advantage of having free/open-source licences for rule-based machine 
translation is that the linguistic knowledge can be reused to build 
knowledge for other language pairs or even for other human language 
technologies besides machine translation, and, conversely, linguistic 
knowledge from other sources may be reused to build machine translation 
systems. The free and open scenario makes this reuse easier, and, if 
copylefted licences are used, builds a commons of knowledge and 
resources that benefits all the language communities involved, and 
specially less-resourced languages, for which large bilingual corpora 
are not available, and morphologically rich languages, which even with 
large corpora suffer from data sparseness.
With the aim of gathering together free/open-source rule-based machine 
translation practitioners and users, the First International Workshop on 
Free/Open-Source Rules-Based Machine Translation was held in November 
2009 at Universitat d'Alacant (Spain). After the success of the first 
edition, a second edition will be held at Universitat Oberta de 
Catalunya (Barcelona, Spain) in January 2011.

Scope:

The main areas of interest for the workshop are as follows:

* Language-independent toolkits, platforms, and frameworks for 
rule-based machine translation
* Language-specific machine translation systems
* Hybrid systems where RBMT is the main component
* Manual and automated evaluation of machine translation systems, 
comparative evaluation of RBMT and SMT/hybrid systems.
* Linguistic resources for RBMT (machine-readable dictionaries, 
part-of-speech taggers, word-sense disambiguators, morphological 
analysers, parsers, etc.)
* Methods for inducing/inferring data for RBMT systems (supervised, 
semi-supervised or unsupervised)
* Interoperability between systems, tools, and data
* Practical descriptions of RBMT integration and usage (in publishing, 
by professional translators, for free/open-source software, etc.)

Note that this is intended as a guideline, and we welcome submissions on 
other aspects of free/open-source rule-based machine translation.

Submissions:

All submissions should be made through the conference management system, 
the url of which is:  http://www.easychair.org/conferences/?conf=freerbmt11

Submissions should describe original work, completed or in progress, be 
anonymous (no authors, affiliations or addresses, and no explicit 
self-reference), be no longer than eight (8) pages of A4, and be in PDF 
format. Initial versions of papers must conform to the conference format 
(http://www.uoc.edu/freerbmt11/freerbmt11.tar.gz).

Where a submission discusses software or data, in final publication it 
will be required to include information on how both the software and the 
data can be publicly accessed. The software and data should be clearly 
licensed under an approved licence. A list of free software licences may 
be found at http://www.fsf.org/licensing/licenses/index_html.

Contact:

If you have questions regarding the submission, please feel free to 
contact the programme committee at submission-freerbmt11 at dlsi.ua.es

For any other questions, please feel free to contact the organisers at 
local-freerbmt11 at uoc.edu

Co-chairs:
   * Juan Antonio Pérez-Ortiz, Universitat d'Alacant
   * Felipe Sánchez-Martínez, Universitat d'Alacant

Programme committee:
   * Juan Antonio Pérez-Ortiz, Universitat d'Alacant
   * Felipe Sánchez-Martínez, Universitat d'Alacant
   * Mikel L. Forcada, Universitat d'Alacant
   * Trond Trosterud, Romssa Universitehta
   * Kevin P. Scannell, Saint Louis University
   * Hrafn Loftsson, Háskólinn í Reykjavík
   * Kepa Sarasola, Euskal Herriko Unibertsitatea
   * Lluís Padró, Universitat Politècnica de Catalunya
   * Antonio Toral, Dublin City University

Local organising committee:
   * Lluís Villarejo, Universitat Oberta de Catalunya
   * Mireia Farrús, Universitat Oberta de Catalunya

_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora


More information about the Corpora mailing list