AnswerFinder at TREC 2005

Diego Molla; Menno van Zaanen

AnswerFinder at TREC 2005

Diego Molla, Menno van Zaanen

School of Computing

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

14 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 language	English
Title of host publication	The Fourteenth text retrieval conference (TREC 2005)
Subtitle of host publication	proceedings
Editors	Ellen M. Voorhees, Lori P. Buckland
Place of Publication	Gaithersburg, MD
Publisher	National Institute of Standards and Technology
Number of pages	9
Publication status	Published - 2006
Event	Text REtrieval Conference (14th : 2005) - Gaithersburg, MD Duration: 15 Nov 2005 → 18 Nov 2005

Conference

Conference	Text REtrieval Conference (14th : 2005)
City	Gaithersburg, MD
Period	15/11/05 → 18/11/05

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/.

Access to Document

Publisher version (open access)Final published version, 137 KBLicence: Unspecified

http://trec.nist.gov/pubs/trec14/papers/macquarieu.qa.pdf

Cite this

@inproceedings{60ac6621c1bd43aeafa4a224c0b2394f,

title = "AnswerFinder at TREC 2005",

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.",

author = "Diego Molla and {van Zaanen}, Menno",

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/.; Text REtrieval Conference (14th : 2005) ; Conference date: 15-11-2005 Through 18-11-2005",

year = "2006",

language = "English",

editor = "Voorhees, {Ellen M.} and Buckland, {Lori P.}",

booktitle = "The Fourteenth text retrieval conference (TREC 2005)",

publisher = "National Institute of Standards and Technology",

address = "United States",

}

TY - GEN

T1 - AnswerFinder at TREC 2005

AU - Molla, Diego

AU - van Zaanen, Menno

N1 - 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/.

PY - 2006

Y1 - 2006

N2 - 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.

AB - 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.

M3 - Conference proceeding contribution

BT - The Fourteenth text retrieval conference (TREC 2005)

A2 - Voorhees, Ellen M.

A2 - Buckland, Lori P.

PB - National Institute of Standards and Technology

CY - Gaithersburg, MD

T2 - Text REtrieval Conference (14th : 2005)

Y2 - 15 November 2005 through 18 November 2005

ER -

AnswerFinder at TREC 2005

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this