Deep Language Workshop 2017

12 September 2017, Université de Montréal
Mila > Events > Deep Language Workshop 2017

Deep Learning has become a key ingredient of progress towards computers which understand and generate language, following pioneering work at MILA more than 15 years ago on neural language models. Modelling, understanding and generating language is a crucial component of artificial intelligence and progress in this field and is also likely to be economically transformative.

This one-day MILA workshop is an opportunity to share advances in this area and is being sponsored by two MILA partners, Microsoft (in particular Maluuba) and Druide.

Attendance is by invitation.

Program

 TimeSpeakerTitle
09:00Yi-Min Wang and Harry ShumOpening and Welcome
09:15Sam Pasupalak and Kaheer SulemanMaluuba: Building Literate Machines
09:25Adam TrischlerMachine Reading Comprehension
09:45Harm van SeijenAchieving Above-Human Performance on Ms. Pac-Man by Reward Decomposition
10:05Simon Lacoste-JulienSeaRNN: Training RNNs with Global-Local Losses
10:25COFFEE BREAK
10:40Jianfeng GaoRecent Progress on MRC and Dialogue
11:00Lihong LiRecent Progress on Reinforcement Learning
11:20Rangan MajumderMachine Comprehension at Bing
11:40Weizhu ChenConversational AI for Enterprises and its Research Challenges
12:00LUNCH BREAK
13:30Yoshua BengioTowards Deep Language Understanding
14:05Alexandre de BrébissonRNNs for Speech Synthesis
14:25Rosemary KeHierarchical attention for QA
14:45COFFEE BREAK
15:00Dmitry BahdanauNatural Language Understanding Challenges
15:20Kian Kenyon-DeanEvent Coreference Resolution
15:40Ethan PerezLearning Visual Reasoning Without Strong Priors
16:00 – 16:10Wrap-up

Location

The workshop will be held on September 12 2017 at Université de Montréal, in room M-415 of Roger-Gaudry building. Wing M is located to the right of the main entrance coming in from Cour d’honneur (L-4).

Address: 2900 Boulevard Edouard-Montpetit, Montréal, QC H3T 1J4

     

 Sponsors

Organization

Organizer: Yoshua Bengio

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }