monzilla.net / research / question answering


the project
status: alive and kicking

description:

Current information retrieval systems allow us to locate documents that might contain the pertinent information, but most of them leave it to the user to extract the useful information from a ranked list. However, users want not whole documents but brief answers to specific questions. Question answering (QA) is meant to be a step closer to real information retrieval in that it attempts to facilitate just that.

The Tequesta (Textual question answering) system, is our first attempt to implement a question answering system.

Like most current QA systems, Tequesta is built on top of a document retrieval system. Here, we use Flexir a home grown retrieval system. For more information on Flexir go to the Document Retrieval Project page.

project members: Christof Monz, Maarten de Rijke

software & other resources
publications
  1. C. Monz and M. de Rijke. Tequesta: The University of Amsterdam's Texual Question Answering System In: Proceedings of Tenth Text Retrieval Conference (TREC-10), 2001, pp. 513-522.
    [ Full text ]

  2. C. Monz. Document Fusion for Comprehensive Event Description In: M. Maybury (ed.) Proceedings of the ACL 2001 Workshop on Human Language Technology and Knowledge Management, 2001.
    [ Full text ]

  3. C. Monz and M. de Rijke. Light-Weight Entailment Checking for Computational Semantics In: P. Blackburn and M. Kohlhase (ed.) Proceedings of the 3rd Workshop on Inference in Computational Semantics (ICoS-3), pp. 59-72.
    [ Full text ]