Dan Roth
homepage:http://l2r.cs.uiuc.edu/
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife

Description

My research focuses on the computational foundations of intelligent behavior. We develop theories and systems pertaining to intelligent behavior using a unified methodology -- at the heart of which is the idea that learning has a central role in intelligence.

My work centers around the study of machine learning and inference methods to facilitate natural language understanding. In doing that I have pursued several interrelated lines of work that span multiple aspects of this problem - from fundamental questions in learning and inference and how they interact, to the study of a range of natural language processing (NLP) problems, including multiple disambiguation problems, shallow parsing, semantic role labeling, co-reference, question answering and textual entailment, to large scale Natural Language Processing and Information Extraction system development - resulting in a number of software packages for NLP tools that are available from my web site and are widely used by the community.


Lectures:

invited talk
flag Amortized Integer Linear Programming Inference
as author at  NIPS Workshops, Lake Tahoe 2013,
1682 views
  opening
flag Opening Ceremony
as author at  25th AAAI Conference on Artificial Intelligence, San Francisco 2011,
together with: Wolfram Burgard,
2678 views
lecture
flag Constraints as Prior Knowledge
as author at  Workshops,
3264 views