Nate Chambers

Published as: Nathanael Chambers
Graduate Student
Natural Language Processing Group


Interests

Most areas of computational semantics interest me. Lately I am working on the shallow semantic interpretation of language, bridging the gap between statistical surface approaches and deep semantics. My current research focuses on learning high level relations between events from large amounts of newswire text. It can also be thought of as script induction, in the Schank style of common sense sequences of situations and events. While a complete world knowledge database of scripts is still out of reach, I believe we can approximate such rich knowledge.

Publications (full list)

Unsupervised Learning of Narrative Event Chains

ACL 2008

Classifying Temporal Relations Between Events.

ACL 2007

Learning Alignments and Leveraging Natural Logic.

ACL 2007

Using Semantics to Identify Web Objects.

AAAI 2006

One-Shot Procedure Learning from Instruction and Observation.

FLAIRS 2006

Chester: Towards a Personal Medical Advisor.

Journal Biomedical Informatics

Real-Time Stochastic Language Generation for Dialogue Systems.

ENLG 2005

more

Recent History

[2003-2006] Florida Institute for Human and Machine Cognition
Dialogue systems, semantic web objects, ontology mapping, language generation

[1998-2003] University of Rochester
M.S. Computer Science: Statistical Language Generation




WeTheTeachers .com

I developed a website in 2005 that encourages teacher collaboration and sharing of resources.
It combines the best of social networks and user based content.

Brian Regan and Script Learning

[Observation]

People that play whole game get a whole snowcone.

[Observation]

And people that play half game get a whole snowcone.

[Conclusion]

So it's always whole, always whole snowcone.

[Goal]

So I'd rather play half game.

[Inference]

I'd rather play half game...still get the whole snowcone.