Comparing Document Retrieval
Strategies in the Context of Question Answering
Christof Monz
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.
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
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).