Workshop on Learning with Structured Data and applications on Natural Language and Biology, Université Paul Sabatier, Toulouse, France
9 - 11 December 2015
Workshop on advances in the Machine Learning field of Structured Prediction.
Abstract: Compositional structures abound in NLP, ranging from bilexical relations, entities in context, sequences and trees. The focus of this talk is in latent-variable compositional models for structured objects that: induce a latent n-dimensional representation for each element of the structure; and learn operators for composing such elements into structures.