Personal tools
A Network of Excellence forging the
Multilingual Europe Technology Alliance

ML4HMT-12 – Proceedings and Slides of the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT

— filed under:

held in conjunction with COLING-2012, Mumbai, India, December 15, 2012

Workshop chairs:
Josef van Genabith, Toni Badia, Christian Federmann, Maite Melero, Marta R. Costa-jussà and Tsuyoshi Okita


Josef van Genabith: Welcome and introductory remarks [slides PDF]

Paper Presentations

  1. Vassilina Nikoulina, Agnes Sandor and Marc Dymetman: Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation [paper PDF] [slides PDF]
  2. Maoxi Li and MingWen Wang: Confusion Network Based System Combination for Chinese Translation Output: Word-Level or Character-Level? [paper PDF] [slides PDF]
  3. Kartik Asooja, Jorge Gracia, Nitish Aggarwal and Asunción Gómez Pérez: Using Cross-Lingual Explicit Semantic Analysis for Improving Ontology Translation [paper PDF] [slides PDF]
  4. Xiaofeng Wu, Tsuyoshi Okita, Josef van Genabith and Qun Liu: System Combination with Extra Alignment Information [paper PDF] [slides PDF]
  5. Tsuyoshi Okita, Antonio Toral and Josef van Genabith: Topic Modeling-based Domain Adaptation for System Combination [paper PDF] [slides PDF]
  6. Tsuyoshi Okita, Raphaël Rubino and Josef van Genabith: Sentence-Level Quality Estimation for MT System Combination [paper PDF] [slides PDF]
  7. Tsuyoshi Okita: Neural Probabilistic Language Model for System Combination [paper PDF] [slides PDF]
  8. Christian Federmann: System Combination Using Joint, Binarised Feature Vectors [paper PDF] [slides PDF]
  9. Christian Federmann, Tsuyoshi Okita, Maite Melero, Marta R. Costa-Jussa, Toni Badia and Josef van Genabith: Results from the ML4HMT-12 Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid Machine Translation [paper PDF] [slides PDF]

Discussion Panel: [Introductory slides PDF]
Panelists: Marc Dymetman, Jan Hajič, Qun Liu, Hans Uszkoreit, Josef van Genabith

  •  The Future of Hybrid MT: is there a single-paradigm winner?
  •  Will we see increasing usage of additional, potentially highly sparse, features?
  •  Will research efforts in Machine Translation and Machine Learning converge?
  •  How do we evaluate progress in terms of translation quality for Hybrid MT?
  •  What are the baselines? Can Human Judgment be integrated?

Invited talk by Jan Hajič (Institute of Formal and Applied Linguistics, Charles University in Prague): Deep Linguistic Information in Hybrid Machine Translation [slides PDF]


Workshop papers [via ACL Anthology]; [via ACL Anthology Searchbench]; [Full Workshop Proceedings in one PDF]; [Workshop homepage]