Second Machine Translation Marathon

Wandlitz, Berlin, 12-17 May 2008



Spring School

Day 1: Introduction to MT and MT Evaluation
Day 2: Word-based models and training
Day 3: Phrase-based models and decoding
Day 4: Factored translation models and discriminative training
Day 5: Tree-based models

Research Showcase

"Translation by Pattern Matching", Adam Lopez, University of Edinburgh
"Improved Word Alignments for Statistical MT", Alex Fraser, University of Stuttgart
"Problems of Deep Syntactic English-to-Czech MT", Ondrej Bojar, Charles University
"Smoothing and Data Selection in Large SMT Systems", Holger Schwenk, LIUM
"Architecture of the Lucy Translation System", Petra Gieselmann, Lucy Software
"Hybrid Architectures for Machine Translation", Andreas Eisele, University of Saarbrücken
"Grammar-based Processing and Re-Usable Hybrid Machine Translation", Stephan Oepen, Norwegian Institute for Science and Technology
"A Data-Driven Approach to Deep Machine Translation", Michael Jellinghaus, University of Saarbrücken

Open Source Convention

"The IRST Language Model Library", Nicola Bertoldi, FBK
"Statistical MT Model Building with MapReduce", Chris Dyer, University of Maryland
"Short range re-ordering using POS tags”, Hieu Hoang, University of Edinburgh
"Roadmap for Moses", Philipp Koehn, University of Edinburgh [not available]
Proposals for Projects [not available]
Reports from Activities at the Open Source Convention [not available]