AnswerFinder at TREC 2005

Diego Molla, Menno van Zaanen

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

1 Downloads (Pure)

Abstract

AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast development of question-answering systems for their deployment in the TREC tasks and other applications. The AnswerFinder modules use XML to express the services they provide, and they can be queried with XML for their services. The QA method now incorporates graph-based methods to compute the answerhood of a sentence and pin-point the answer. The system uses a set of graph-based rules that are learnt automatically. Unfortunately the system could not be completed and debugged before the TREC deadline and the runs did not fare well. Currently we are debugging and evaluating the system.
Original languageEnglish
Title of host publicationThe Fourteenth text retrieval conference (TREC 2005)
Subtitle of host publicationproceedings
EditorsEllen M. Voorhees, Lori P. Buckland
Place of PublicationGaithersburg, MD
PublisherNational Institute of Standards and Technology
Number of pages9
Publication statusPublished - 2006
EventText REtrieval Conference (14th : 2005) - Gaithersburg, MD
Duration: 15 Nov 200518 Nov 2005

Conference

ConferenceText REtrieval Conference (14th : 2005)
CityGaithersburg, MD
Period15/11/0518/11/05

Bibliographical note

Version archived for private and non-commercial use with the permission of the author and according to publisher conditions. For further reproduction rights please contact the publisher at http://trec.nist.gov/.

Fingerprint Dive into the research topics of 'AnswerFinder at TREC 2005'. Together they form a unique fingerprint.

Cite this