Title: Better Natural Language Analysis and
       Amortized Integer Linear Programming 

Abstract:
Computational approaches to problems in Natural Language Understanding and
Information Extraction are often modeled as structured predictions that involve
assigning values to sets of interdependent variables. Over the last few years,
one of the most successful approaches to studying these problems involves 
Constrained Conditional Models (CCMs), an Integer Learning Programming 
formulation that augments probabilistic models with declarative constraints as
a way to support such decisions.

I will present research within this framework, focusing on learning and
inference issues and, in particular, will present recent results on Extending
Semantic Role Labeling to additional predicates and on Amortized Inference
learning to accelerate inference during the life time of the learning system.
If there is time, I may mention some work on Wikification and coreference
resolution done within this computational framework.