Machine Translation Summit XIV, Nice, France
2 - 6 September 2013
Home
Organization
Call for papers
Programme
Proceedings
Tutorials
Workshops
Social Programme
Important Dates
Registration
Hotel Booking
Excursions
Exhibition opportunities
Projects Village
Sponsor opportunities
Conference venue
About Nice
How to get here
Contact us
Links
 

Tutorial 2: Monday, 2 SEPT 2013, 2 pm - 6 pm

Domain Adaptation in Machine Translation

Organized by:
   Cristina Vertan,University of Hamburg, Research Group "Computerphilology"
   Mirela-Stefania Duma, University of Hamburg, Natural Language Systems Division

There was a massive progress in Machine Translation during the last couple of years. Systems performing translation for assimilation are available for various language pairs and rely mainly on statistical methods, which means on the availability of large amount of training data in form of parallel corpora. The dependency between the quality of the output and the type and quantity of the training material leads to the problem of domain adaptation. The output of a machine translation system from a different domain than the one of training corpus will have significant lower accuracy.

As it is impossible to built large parallel corpora for all possible domains and language pairs, current research focuses currently on domain adaptation methods.

State of the art domain adaptation techniques can be classified in:

  • Alignment domain adaptation
  • Language Model Adaptation
  • Translation Model Adaptation
  • Reordering model Adaptation

The tutorial intends to give a broad overview on domain adaptation methods in statistical machine translation and discuss also aspects of this topic, which are also for other machine translation paradigms like Example Based machine Translation or Rule-based Machine Translation.

The first part of the tutorial will focus on problems which MT-systems face when they are exposed to different type of input as they were trained / or for which resources were built.

Part II of the tutorial will introduce methods for domain adaptation in statistical machine translation, as listed above

Part III is dedicated to problems of domain adaptation for other machine translation paradigms

Finally the last part will deal with open problems and will present a practical case of domain adaptation, the ATLAS-System in which an MT-Engine was embedded into a web content management system. Domain adaptation was performed for 13 domains and 15 language pairs.

Tutotial website: http://www.c-phil.uni-hamburg.de/view/Main/DomainAdaptation2013

   

LATEST NEWS:

September 11, 2013

List of Participants available. Click here

August 25, 2013

Main conference proceedings are on-line. Click here

August 24, 2013

Workshop proceedings are on-line. Click here

July 28, 2013

Detailed programme now available here

June 20, 2013

Accepted papers announced see Programme

March 26, 2013

MT Summit registration opened

March 15, 2013

Paper submission deadline has been extended to April 22, 2013

March 3, 2013

Call for Workshop papers disseminated

February 16, 2013

Four workshop proposals have been accepted.

February 2, 2013

Deadline for submission of Tutorial proposals has been extended to the 15. FEB 2013

January 28, 2013

Call for User Papers/ Presentations disseminated

December 26, 2012

Call for tutorial proposals disseminated

December 26, 2012

Call for workshop proposals disseminated

December 8, 2012

Call for research papers published see Call for Papers