The Evolving Research Landscape in Statistical Machine Translation
About the speaker
After briefly introducing the basic concepts of statistical machine translation, we will present a non-technical overview of recent and current research in that area. Our survey will cover a broad spectrum of themes, including the following ones:
- System evaluation
- Acquisition of training data
- Phrase-based models: training and "decoding"
- Word order and syntax
- System adaptation
- Multilingual coverage
- System combination techniques
- SMT-based tools for translators
We will also discuss the extent of recent technological progress in translation accuracy and system performance.
Organized on the occasion of the public defense of Lieve Macken's PhD dissertation entitled "Sub-Sentential Alignment of Translational Correspondences" (promotors Walter Daelemans and Joost Buysschaert) on Friday May 28, 2010 at the University of Antwerp. You are all kindly invited to the public defense which starts at 3PM. The address is: Promotiezaal, Gebouw van de Grauwzusters, Lange St. Annastraat 7, 2000 Antwerpen. (Building S on the Campus Map)
C 104, University of Antwerp, Prinsstraat 13, 2000 Antwerpen
C 104 is in Building C on the Campus Map
Sponsored by CLIF, the scientific research community for Computational Linguistics and Language Technology.
[17 registered participants]