Abstract:

The maturity of machine learning techniques allows us today to
learn many low level natural language predicates and generate an
appropriate vocabulary over which reasoning methods can be used to
make significant progress in natural language understanding.

I will describe research on a framework that combines learning and
inference. Our Inference with Classifiers approach allows the
output of local classifiers for different problem components to be
assembled into a whole that reflects global preferences and
constraints. Examples will be drawn from ‘wh’ attribution in
natural language processing (determining who did what to whom when
and where) and textual entailment (determining whether one
utterance is a likely consequence of another).

The talk will be accessible to students.