This page is for information related to the ongoing research seminar, such as schedule, pointers to relevant papers, etc.

Entry in the CoLi KVV

Schedule

Proposed topics

• Architectures for hybrid/multi-engine MT
• Improving MT by shallow NLP techniques
  
• Syntax-based MT
  
• Language modeling for MT, confidence estimation
  
• Machine Learning for MT
  
• Techniques for MT evaluation
  
• Triangulation, exploiting n-way parallel corpora
  
• Work in related projects (SMART, METIS)

Proposed readings

• Architectures for hybrid/multi-engine MT
• Multi-Engine Machine Translation with an Open-Source SMT Decoder, Chen et al., WMT 2007
  
• Combining Translations from Multiple Machine Translation Systems, Rosti et al., HLT-NAACL2007 best paper
• Statistical Post-Editing on SYSTRAN’s Rule-Based Translation System, Loïc Dugast, Jean Senellart and Philipp Koehn, WMT 2007
• Rule-Based Translation with Statistical Phrase-Based Post-Editing, Michel Simard, Nicola Ueffing, Pierre Isabelle and Roland Kuhn, WMT 2007
• Towards Hybrid Quality-Oriented Machine Translation, draft paper from the Norwegian LOGON project (also fits into syntax-based MT)
• Improving MT by shallow NLP techniques
• TBD
  
• Syntax-based MT
• Grammatical machine translation, Riezler, Maxwell, HLT-NAACL'06
• The Syntax Augmented MT (SAMT) System at the Shared Task for the 2007 ACL Workshop on Statistical Machine Translation, Andreas Zollmann, Ashish Venugopal, Matthias Paulik and Stephan Vogel
• Labelled Dependencies in Machine Translation Evaluation, Karolina Owczarzak, Josef van Genabith and Andy Way, WMT 2007
• list of many more papers TDB
  
• Language modeling for MT, confidence estimation
• Randomised Language Modelling for Statistical Machine Translation, David Talbot and Miles Osborne, ACL 2007
• Smoothed Bloom filter language models: Tera-Scale LMs on the Cheap, David Talbot and Miles Osborne, EMNLP 2007
• Efficient Handling of N-gram Language Models for Statistical Machine Translation, Marcello Federico and Mauro Cettolo, WMT 2007
  

• Large Language Models in MT, Thorsten Brants, Ashok C. Popat, Peng Xu, Franz J. Och and Jeffrey Dean, EMNLP-CoNLL 2007
  

• Machine Learning for MT
• papers TBD
  
• Techniques for MT evaluation
• (Meta-) Evaluation of Machine Translation Chris Callison-Burch, Cameron Fordyce, Philipp Koehn, Christof Monz and Josh Schroeder, WMT 2007
• METEOR: An Automatic Metric for MT Evaluation with High Levels of Correlation with Human Judgments, Alon Lavie and Abhaya Agarwal, WMT 2007
  
• Word Error Rates: Decomposition over POS classes and Applications for Error Analysis, Maja Popovic and Hermann Ney, WMT 2007
  
• more TBD
  
• Triangulation, exploiting n-way parallel corpora
• Triangulation, Martin Kay
• Text-translation Alignment: Three Languages Are Better Than Two, Michel Simard, EMNLP/VLC-99
• Statistical Multi-Source Translation, Franz Josef Och, Hermann Ney, MT Summit 2001
• Parallel Corpora and Phrase-Based Statistical Machine Translation for New Language Pairs via Multiple Intermediaries, A. Eisele, LREC 2006
  
• Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora, Trevor Cohn and Mirella Lapata. ACL 2007
  
• Work in related projects (SMART, METIS)
• list of papers TBD