论文信息 - Preprocessing documents to answer Dutch questions

Preprocessing documents to answer Dutch questions

We describe a framework for offline extraction of certain types of information from a document collection, and discuss its usage for answering factoid questions. We implemented this approach as a part of the Dutch Question Answering System developed at the University of Amsterdam. The evaluation of the system using data from the CLEF 2003 Question Answering track shows that our strategy yields a significant improvement in the performance of our overall system.

Gilad Mishne | Valentin Jijkoun | M. de Rijke | V. Jijkoun | G. Mishne

[1] Ellen Riloff,et al. Automatically Generating Extraction Patterns from Untagged Text , 1996, AAAI/IAAI, Vol. 2.

[2] Nelleke Oostdijk,et al. The Spoken Dutch Corpus. Overview and First Evaluation , 2000, LREC.

[3] M. de Rijke,et al. Tequesta: The University of Amsterdam's Textual Question Answering System , 2001, TREC.

[4] Robert F. Simmons,et al. Answering English questions by computer: a survey , 1965, CACM.

[5] Thorsten Brants,et al. TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.

[6] J. Davenport. Editor , 1960 .

[7] Ellen M. Voorhees,et al. Overview of the TREC 2002 Question Answering Track , 2003, TREC.

[8] Ellen M. Voorhees,et al. The eleventh text REtrieval conference, TREC 2002 , 2003 .