The "Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT" is an effort to trigger systematic investigation on improving state-of-the-art Hybrid MT, using advanced machine-learning (ML) methodologies. The main focus of the shared task 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?
Registration
Participation is free!
You can download the workshop programme (45 KB) here. You can also see the original call for papers.
| 9:15 | Welcome |
| 9:30 | Toni Badia (BM) — Introduction to the ML4HMT Shared Task Workshop |
| 9:40 | Patrik Lambert (LIUM) — The MANY System @ML4HMT-2011 (198 KB) · presentation slides (786 KB) |
| 10:30 | Tsuyoshi Okita (DCU) — DCU System Combination @ML4HMT-2011 (196 KB) · presentation slides (208 KB) |
| 11:00 | Eleftherios Avramidis (DFKI) — DFKI System Combination with Sentence Ranking @ML4HMT-2011 (106 KB) · presentation slides (614 KB) |
| 11:30 | Coffee Break |
| 12:00 | Christian Federmann (DFKI) — DFKI System Combination using Syntactic Information @ML4HMT-2011 (148 KB) · presentation slides (748 KB) |
| 12:30 | Christian Federmann (DFKI) — Comparison of Overall Results @ML4HMT-2011 (539 KB) · presentation slides (1 MB) |
| 12:40 | Alon Lavie (CMU) — MEMT: Alignment-based MT System Combination with Linguistic and Statistical Features · presentation slides (1.1 MB) |
| 13:10 | Discussion Panel Chair: Patrik Lambert (LIUM), Alon Lavie (CMU), Cristina España-Bonet (UPC) and Christian Federmann (DFKI). Topics include:
|
| 14:00 | Lunch |