BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:flint63

The blue social bookmark and publication sharing system.

(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)

Looking Under the Hood: Tools for Diagnosing Your Question Answering Engine

by: Eric Breck, Marc Light, Gideon Mann, Ellen Riloff, Brianne Brown, Pranav Anand, Mats Rooth, and Michael Thelen

In: Proceedings of the ACL 2001 Workshop on Open-Domain Question Answering, Toulouse, France (2001) , p. 1-8.

Resources (URL, PDF, PS...)

URL:	http://www.aclweb.org/anthology/W01-1201
DOI:	10.3115/1117856.1117857

In this paper we analyze two question answering tasks: the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification, and answer typing for short answer extraction. We present general tools for analyzing the strengths and limitations of techniques for these subproblems. Our results quantify the limitations of both term overlap and answer typing to distinguish between competing answer candidates.

BibTeX record

@inproceedings{BreckLightEtAl01ACL,
  abstract = {In this paper we analyze two question answering tasks: the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification, and answer typing for short answer extraction. We present general tools for analyzing the strengths and limitations of techniques for these subproblems. Our results quantify the limitations of both term overlap and answer typing to distinguish between competing answer candidates.},
  added-at = {2010-10-29T17:02:14.000+0200},
  author = {Breck, Eric and Light, Marc and Mann, Gideon and Riloff, Ellen and Brown, Brianne and Anand, Pranav and Rooth, Mats and Thelen, Michael},
  biburl = {http://www.bibsonomy.org/bibtex/2e938893c6f9a643e6366300be08760d5/flint63},
  booktitle = {Proceedings of the ACL 2001 Workshop on Open-Domain Question Answering, Toulouse, France},
  doi = {10.3115/1117856.1117857},
  file = {ACL Anthology:2001/BreckLightEtAl01ACL.pdf:PDF},
  interhash = {5900e2302dcb6bf3b568e38722dbefcf},
  intrahash = {e938893c6f9a643e6366300be08760d5},
  keywords = {information acl test paper answer retrieval interface zzz.th.c4 ai v1010 processing language user},
  pages = {1-8},
  timestamp = {2010-10-29T17:02:14.000+0200},
  title = {Looking Under the Hood: Tools for Diagnosing Your Question Answering Engine},
  url = {http://www.aclweb.org/anthology/W01-1201},
  year = 2001
}

Endnote record

%0 Conference Paper
%1 BreckLightEtAl01ACL
%A Breck, Eric
%A Light, Marc
%A Mann, Gideon
%A Riloff, Ellen
%A Brown, Brianne
%A Anand, Pranav
%A Rooth, Mats
%A Thelen, Michael
%B Proceedings of the ACL 2001 Workshop on Open-Domain Question Answering, Toulouse, France
%D 2001
%K 
%P 1-8
%T Looking Under the Hood: Tools for Diagnosing Your Question Answering Engine
%R 10.3115/1117856.1117857
%U http://www.aclweb.org/anthology/W01-1201
%X In this paper we analyze two question answering tasks: the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification, and answer typing for short answer extraction. We present general tools for analyzing the strengths and limitations of techniques for these subproblems. Our results quantify the limitations of both term overlap and answer typing to distinguish between competing answer candidates.

BibSonomy :: publication ::

Looking Under the Hood: Tools for Diagnosing Your Question Answering Engine

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record