Freerbmt11
Second International Workshop on Free/Open-Source Rule-Based Machine Translation
20th—21st January 2011
Universitat Oberta de Catalunya, Barcelona (Spain)
Introduction
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 (RB) systems built on these principles are still little known. Both SMT and RBMT paradigms have pros and cons 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 Rule-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, morphological analysers, syntactic or semantic parsers etc.)
- Methods for inducing/inferring data for RBMT systems (supervised, semi-supervised or unsupervised)
- Interoperability between systems, tools, data
- Practical descriptions of RBMT integration and usage (in publishing, by professional translators, for free/open-source software)
- Note that this is intended as a guideline, and we welcome submissions on other aspects of free and open-source rule-based machine translation.
Important dates
8th November - Submission deadline
22nd November - Notification to authors
6th December - Deadline for camera-ready copy
20th—21st January - Workshop
Submissions
All submissions should be made through the conference management system, the url of which is: [1]
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, which can be found in 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 publically accessed. The software and data should be clearly licensed under an approved licence. A list of free software licences may be found at [2].
All the papers included in the proceedings will be made available through UOC's open access institutional repository.
If you come across any problem with your submission, please do not hesitate to contact the organisers at submission-freerbmt11@dlsi.ua.es.
Registration
To be announced
Venue
The workshop will take place at UOC's Support Centre at Barcelona, which is conviniently located at the very heart of Barcelona.
Map
In short we will provide suggestions for accomodation. Further information about Barcelona can be found on Wikipedia and Wikitravel.
Invited speakers
To be announced
Programme
To be announced
Proceedings
All the papers included in the proceedings will be made available through UOC's open access institutional repository.
Organisers
Co-chairs
Juan Antonio Pérez-Ortiz, Universitat d'Alacant
Felipe Sánchez-Martínez, Universitat d'Alacant
Local organising committee
Lluís Villarejo, Universitat Oberta de Catalunya
Mireia Farrús, Universitat Oberta de Catalunya
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
Contact
If you have questions regarding the submission, please feel free to contact the programme committee at [submission-freerbmt11@dlsi.ua.es].
For any other questions, please feel free to contact the organisers at local-freerbmt11@uoc.edu.
Supported by
- Group Transducens, DLSI, Universitat d'Alacant
- Universitat Oberta de Catalunya
- Prompsit Language Engineering
- European Association for Machine Translation
(More to be added)
