Comparing Document Retrieval Strategies in the Context of Question Answering

Christof Monz

University of Amsterdam


UMIACS Computational Linguistics Colloquium

November 26, 2003,
11:00am, AVW Room 2120


 

Current question answering systems rely on document retrieval as a means of providing documents which are likely to contain an answer to a user's question. A question answering system heavily depends on the effectiveness of a retrieval system: If a retrieval system fails to find any relevant documents for a question, further processing steps to extract an answer will inevitably fail, as well. In this talk, I compare the effectiveness of some standard retrieval techniques with respect to their usefulness for question answering. I also introduce a new locality-based retrieval technique which shows significant improvements over existing approaches.

About the speaker:

Christof Monz received a degree in computational linguistics from the University of Stuttgart, Germany, in 1999. He is currently completing his PhD studies in computer science at the University of Amsterdam.  His research interests include information retrieval, corpus-based question answering, and statistical natural language processing.

For the colloquium series schedule, see the UMD Computational Linguistics Colloquium Series web page at http://umiacs.umd.edu/~resnik/cl_colloquium/. If you are interested in meeting with the speaker, please contact Doug Oard (oard@umiacs.umd.edu).