NEW !
Invited Talk - Makoto Nagao, National Institute of Information and Communications Technology, Japan -- Abstract
In the current globalized communications scene, both machine and computer-aided translation have become key technologies. Indeed, a recent survey regarding ten emerging technologies that will change the world, placed Machine Translation at the leading number one position. It is expected that with the increased number of official languages in Europe, and the continuing growth of non-English Internet resources, machine translation and computer-aided translation systems will become indispensable tools in everyday work.
Machine Translation is a complex scientific task involving almost every aspect of natural language processing. Following the developments in language technology, during the last 10 years, corpus-based approaches to machine translation (statistical or example-based) tried, and partially succeeded to replace traditional rule-based approaches. The main advantage of corpus-based machine translation systems is that they are self-customising in the sense that they can learn the translations of terminology and even stylistic phrasing from previously translated materials.
However, after a first enthusiastic period it turned out that pure corpus-based methods also have limitations, which can only be overcome by introducing linguistic knowledge. Therefore current research focuses on hybrid methods, combining data-driven (corpus) and rule-driven methods. On the other hand, more practical CAT applications such as translation memories and bilingual concordancers along with the extensive use of electronic dictionaries and term tools/banks, emerged as popular, vital tools for professional translators.
The current workshop aims to bring together researchers working in machine and machine-aided translation. The workshop will alternate paper presentations with panel discussions. Main topics of interest are:
- Hybrid approaches to machine translation
- Recent advances in machine aided translation
- Evaluation of MT and CAT systems
- Impact of Semantic Web activities on MT and CAT systems.
- Tools for professional translators
We welcome original papers related (but not limited) to one or more of the following topics:
- Learning from parallel aligned corpora
- Integration of statistical and example-based approaches
- Statistical support for rule-based machine translation
- Dynamic combination of example–based machine translation or translation memories with rule-based approaches
- Template learning in example based machine translation
- Integration of Termbases, Translation Memories, and Parallel Corpora
- Evaluation criteria for MT and CAT systems
- Usage of semantic web-ontologies for machine translation
- Usage of semantic web annotations in corpus-based machine translation
- Perspectives of grid technologies for MT and CAT systems.
- Practical MT systems (MT for professionals, MT for multilingual eCommerce, MT for localization
- Automatic and semiautomatic acquisition of bilingual and multilingual lexica
- Practical CAT tools (Translation memories, bilingual concordancers, terminology tools and resources)
- Use of corpora in translation
We also encourage demonstrations of developed tools. Submissions for a demonstration session should include a 2 page demo-note describing the system-architecture and performance as well as technical requirements.
- Walther v. Hahn (University of Hamburg)
- John Hutchins (EAMT)
- Cristina Vertan (University of Hamburg)