UdeM-McGill-MITACS machine learning seminar Tues Jan. 22, 10:00am, PAA 3195
The UdeM-McGill-MITACS seminar series will resume next week with its first 2008 seminar. Note the new time for the seminars.
Next week's seminar (see http://www.iro.umontreal.ca/article.php3? id_article=107&lang=en):
Open Problems in Statistical Machine Translation
by Roland Kuhn, Institute for Information Technology National Research Council of Canada
Location: Pavillon André-Aisenstadt (UdeM), room 3195 Time: January 22nd 2008, 10h00
Since around the year 2000, the dominant paradigm in research on machine translation has changed from an “expert system” approach to one based on machine learning, called “statistical machine translation” (SMT). The purpose of the talk is to give an overview of SMT and to encourage researchers in machine learning to consider entering the field. After a description of how the SMT systems are evaluated experimentally, the five IBM translation models will be summarized. Then, the key concepts underlying today’s phrase-based SMT systems will be described. Finally, the talk will discuss five interesting open problems in SMT: system adaptation, feature selection, generalizing beyond phrases, discriminative training of SMT systems, and the application of kernel methods to SMT.
Afficher les réponses par date
On Wednesday 16 January 2008 13:35:20 Hugo Larochelle wrote:
Open Problems in Statistical Machine Translation
Hugo,
Is it possible to publicize my talk tomorrow on this UdeM-McGill-MITACS list? Since they both talk about MT, they are germane.
Thanks, Joseph
The UdeM-McGill-MITACS seminar series resumes this week with its first 2008 seminar. Note the new time for the seminars.
Next week's seminar (see http://www.iro.umontreal.ca/article.php3? id_article=107&lang=en):
Open Problems in Statistical Machine Translation
by Roland Kuhn, Institute for Information Technology National Research Council of Canada
Location: Pavillon André-Aisenstadt (UdeM), room 3195 Time: January 22nd 2008, 10h00
Since around the year 2000, the dominant paradigm in research on machine translation has changed from an “expert system” approach to one based on machine learning, called “statistical machine translation” (SMT). The purpose of the talk is to give an overview of SMT and to encourage researchers in machine learning to consider entering the field. After a description of how the SMT systems are evaluated experimentally, the five IBM translation models will be summarized. Then, the key concepts underlying today’s phrase-based SMT systems will be described. Finally, the talk will discuss five interesting open problems in SMT: system adaptation, feature selection, generalizing beyond phrases, discriminative training of SMT systems, and the application of kernel methods to SMT.
lisa_seminaires@iro.umontreal.ca
-
Hugo Larochelle -
Joseph Turian