DFKI-LT - Proceedings of the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT

Josef van Genabith, Toni Badia, Christian Federmann, Maite Melero, Marta R. Costa-jussą, Tsuyoshi Okita
Proceedings of the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT
1 The COLING 2012 Organizing Committee, Mumbai, India, 12/2012
 
We are delighted to welcome you to the of the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT and associated Shared Task (ML4HMT- 2012) in Mumbai. The Shared Task is an effort to trigger systematic investigation on improving state-of-the-art Hybrid MT, using advanced machine-learning (ML) methodologies. Its main focus is trying to answer the following question: Can Hybrid/System Combination MT techniques benefit from extra information (linguistically motivated, decoding and runtime) from the different systems involved? Participants to the challenge are requested to build hybrid translations by combining the output of several MT systems of different types. Five participating combination systems, each following a different solution strategy, have been submitted to the shared task. The Workshop will be composed of two parts. In the first part we will have an invited talk and the presentation of three research papers. In the second part, participants to the shared task will describe their systems and results. At the end of this part, there will be a presentation of the joint evaluation, followed by a discussion panel. We are looking forward to an interesting workshop and want to thank all authors, presenters and attendees for making this a successful workshop.
 
Files: BibTeX, W12-57.pdf