AMTA 2014
WORKSHOP ON
INTERACTIVE AND ADAPTIVE
MACHINE TRANSLATION

22 October 2014
Vancouver, Canada

The increasing use of machine translation in the workflow of professional translators creates demand for machine translation technology that provides more interactive collaboration, learns from its errors and adapts to the translators' style and adapts the underlying machine translation system online to the specific needs of the translator for the given task.

The next generation of computer aided translation (CAT) tools has to move beyond the use of static machine translation for human post-editing into a much richer division of labor between man and machine that takes full advantage of man's understanding of content and machine's greater ability to quickly process large amounts of data.

On the other hand, these tools will allow a more friendly interaction between the human and the machine through the use of different modalities of interactions as speech, gaze tracking, e-pen, etc. Finally, all of these issues will lead to an increase of the productivity of the professional translators.

Such tools are in development in a number of research labs across the world, one example is the open source workbench developed by the EU-funded projects Matecat and Casmacat, led by the organizers of this workshop.

This workshop brings to together researchers in this nascent subfield of machine translation. The workshop will divide its schedule about equally between invited talks by leading researchers and paper presentations on more recent advances.

SCHEDULE

8:45amOpening Remarks
 
Invited Talks
9amMeasuring Translation Productivity Offline -
Some commercial challenges and research opportunities apparent from the iOmegaT project
John Moran, Trinity College / CNGL
9:30amMixed-initiative Human Language Translation
Spence Green, Stanford
10amOnline and Active Learning for Machine Translation and Computer-Assisted Translation
Jesús González-Rubio, Universitat Politècnica de València
 
10:30am  Coffee Break
 
Invited Talks
11amTranslators, Machine Translation and Trust
Michel Simard, National Research Council Canada
11:30amLearning from Post-Editing: Real Time Model Adaptation for Machine Translation
Michael Denkowski, CMU
12pmUser-Adaptative MT in the MateCat Tool
Marcello Federico, Fondazione Bruno Kessler
12:30pmThe Human Language Model
Lane Schwartz, University of Illinois at Urbana-Champaign
 
1pmLunch
 
2:30pmPanel Discussion
 
3:30pmCoffee Break
 
4pmPoster Session
Integrating Online and Active Learning in a Computer-Assisted Translation Workbench
Vicent Alabau, Jesús González-Rubio, Daniel Ortiz-Martínez, Germán Sanchis Trilles, Francisco Casacuberta, Mercedes García-Martínez, Bartolomé Mesa-Lao, Dan Cheung Petersen, Barbara Dragsted and Michael Carl

Towards a Combination of Online and Multitask Learning for MT Quality Estimation: a Preliminary Study
José G. C. de Souza, Marco Turchi and Matteo Negri

Predicting Post-Editor Profiles from the Translation Process
Karan Singla, David Orrego Carmona, Ashleigh Rhea Gonzales, Michael Carl and Srinivas Bangalore

Optimized MT Online Learning in Computer Assisted Translation
Prashant Mathur and Cettolo Mauro

Behind the Scenes in an Interactive Speech Translation System
Mark Seligman and Mike Dillinger

Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario
Ulrich Germann

ORGANIZERS

Francisco Casacuberta, Universitat Politècnica de València
Marcello Federico, Fondazione Bruno Kessler
Philipp Koehn, University of Edinburgh / Johns Hopkins University

PROGRAM COMMITTEE

Vicent Alabau (Universitat Politècnica de València)
Loïc Barrault (Université du Maine)
Frédér Blain (Université du Maine)
Christian Buck (University of Edinburgh)
Chris Dyer (Carnegie Mellon University)
Mikel L. Forcada (Universitat d'Alacant)
George Foster (National Research Council, Canada)
Jesús González-Rubio (Universitat Politècnica de València)
Roland Kuhn (National Research Council, Canada)
Mauro Cettolo (Fondazione Bruno Kessler)
Matteo Negri (Fondazione Bruno Kessler)
Jan Niehues (Karlsruhe Institute of Technology)
Daniel Ortiz-Martínez (Universitat Politècnica de València)
Juan Antonio Pérez-Ortiz (Universitat d'Alacant)
Holger Schwenk (Université du Maine)
Patrick Simianer (Universität Heidelberg)
Lucia Specia (University of Sheffield)
Marco Turchi (Fondazione Bruno Kessler)
Enrique Vidal (Universitat Politècnica de València)
Katharina Wäschle (Universität Heidelberg)
François Yvon (LIMSI/CNRS, Orsay)

CONTACT

For questions, comments, etc. please send email to pkoehn@inf.ed.ac.uk.

Supported by the European Commision
under the Matecat and CASMACAT projects (grants 287688 and 287576).