Hi All,
This week we return to our normal tea talk schedule with Antoine Bordes, who will tell us about some fascinating work he did before joining LISA. Title and abstract below.
When: Thursday Sept. 16th, 2:30pm Where: LISA lab (AA3256)
Hope to see you all there.
Towards Understanding Situated Natural Language -- Joint work with J. Weston (Google), N. Usunier (Paris 6) and R. Collobert (NEC) --
We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of hand-crafted rules or features.
Paper and data available from http://www-etud.iro.umontreal.ca/~bordesa/mywiki/doku.php?id=abstract_babi_a... .
Cheers, Aaron