Lisa_seminaires Janvier 2008

lisa_seminaires@iro.umontreal.ca

3 participants
3 discussions

UdeM-McGill-MITACS machine learning seminar Tues Jan. 22, 10:00am, PAA 3195
by Hugo Larochelle 21 Jan '08

21 Jan '08

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.

2 2

Fwd: Séminaire RALI-OLST: JEUDI le 17 janvier
by Yoshua Bengio 17 Jan '08

17 Jan '08

Begin forwarded message: > From: Guy Lapalme <lapalme(a)iro.umontreal.ca> > Date: January 9, 2008 9:07:44 PM EST > To: rali-olst(a)iro.umontreal.ca > Subject: Séminaire RALI-OLST: JEUDI le 17 janvier > > Large-Scale Structure Prediction by Classification > Joseph Turian > Laboratoire LISA, DIRO > JEUDI 17 janvier, 11:30, Salle 3195, Pavillon André-Aisenstadt > ^^^^^ Jour de la semaine inhabituel > > We present an approach to structure prediction based upon a reduction > to binary classification. This binary classification task typically > involves many examples and many features. We propose a learning method > for these large-scale classification tasks that is simple, accurate, > and efficient. We apply this approach large-scale structure prediction > problems in NLP: parsing and machine translation. > > Guy Lapalme > 514-343-2145

2 1

Fwd: ML talk @SOCS - this Thursday!
by Hugo Larochelle 15 Jan '08

15 Jan '08

This talk might be of interest for people on this mailing list. Hugo Début du message réexpédié : > De : "Joelle Pineau" <jpineau(a)cs.mcgill.ca> > Date : 15 janvier 2008 13:46:28 HNE > À : labrl(a)cs.mcgill.ca > Cc : erica.moodie(a)mcgill.ca, pbiernot(a)gmail.com, > larocheh(a)iro.umontreal.ca, aaron.courville(a)gmail.com > Objet : ML talk @SOCS - this Thursday! > Répondre à : jpineau(a)cs.mcgill.ca > > Hi everyone, > > Eric Laber, a PhD candidate with Susan Murphy at the U. of > Michigan, will > be visiting the RLLab from Jan.16 to Jan.21. > > He'll be giving a talk on his recent research on Thursday Jan.17, > 2:30pm, > in the Trottier buildling, Rm 0070. **Note the unusual place/ > time.** The > abstract is included below. This should be of significant interest > to the > machine learning crowd. > > If you'd like to meet with Eric while he's here, or are free to > take him > to dinner, please let me know. > > Feel free to forward to any interested colleagues. > > cheers, > Joelle

1 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Janvier 2008