BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:diego_ma

The blue social bookmark and publication sharing system.

entry of diego_ma:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Towards Answer Extraction: An Application to Technical Domains

by: Fabio Rinaldi, James Dowdall, Michael Hess, Diego Mollá, and Rolf Schwitter

In: Proc. ECAI2002 July 21-26 2002, Lyon, France Amsterdam: IOS Press (2002) , p. 460-464.

Resources (URL, PDF, PS...)

URL:	http://www.ifi.unizh.ch/staff/rinaldi/

The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction AE systems satisfy that need. This paper presents one such system ExtrAns which works by transforming documents and queries into a semantic representation called Minimal Logical Form MLF and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.

BibTeX record

@inproceedings{Rinaldi:2002,
  abstract = {The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems satisfy that need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.},
  added-at = {2008-01-29T08:59:29.000+0100},
  address = {Amsterdam},
  author = {Rinaldi, Fabio and Dowdall, James and Hess, Michael and Moll{\'a}, Diego and Schwitter, Rolf},
  biburl = {http://www.bibsonomy.org/bibtex/2a9862cf4812a9496453656806f9f2a16/diego_ma},
  booktitle = {Proc. ECAI2002 July 21-26 2002, Lyon, France},
  editor = {van Harmelen, Frank},
  interhash = {24563ca9f22cb07b18cbd0003fd4255c},
  intrahash = {a9862cf4812a9496453656806f9f2a16},
  keywords = {ExtrAns molla_publication},
  pages = {460-464},
  publisher = {IOS Press},
  timestamp = {2008-01-29T08:59:29.000+0100},
  title = {Towards Answer Extraction: An Application to Technical Domains},
  url = {http://www.ifi.unizh.ch/staff/rinaldi/},
  year = 2002
}

Endnote record

%0 Conference Paper
%1 Rinaldi:2002
%A Rinaldi, Fabio
%A Dowdall, James
%A Hess, Michael
%A Moll{\'a}, Diego
%A Schwitter, Rolf
%B Proc. ECAI2002 July 21-26 2002, Lyon, France
%C Amsterdam
%D 2002
%E van Harmelen, Frank
%I IOS Press
%K 
%P 460-464
%T Towards Answer Extraction: An Application to Technical Domains
%U http://www.ifi.unizh.ch/staff/rinaldi/
%X The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems satisfy that need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.

BibSonomy :: publication ::

Towards Answer Extraction: An Application to Technical Domains

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record