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)

Named Entity Recognition in Question Answering of Speech Data

by: Diego Mollá, Menno van Zaanen, and Steve Cassidy

In: Proc. ALTW 2007, Vol. 5 (2007) , p. 57-65.

Resources (URL, PDF, PS...)

URL:	http://www.alta.asn.au/events/altw2007/cdrom/index.html

Question answering on speech transcripts QAst is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity NE recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names gazetteers and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second out of three participants in one of the QAst subtasks.

BibTeX record

@inproceedings{Moll'a:2007,
  abstract = {Question answering on speech transcripts (QAst) is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity (NE) recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second (out of three participants) in one of the QAst subtasks.},
  added-at = {2008-01-29T07:21:37.000+0100},
  author = {Moll{\'a}, Diego and van Zaanen, Menno and Cassidy, Steve},
  biburl = {http://www.bibsonomy.org/bibtex/2202b97875a0ca06dba67da3f7febfc86/diego_ma},
  booktitle = {Proc. ALTW 2007},
  editor = {Colineau, Nathalie and Dras, Mark},
  interhash = {2606e7117807640622c8c6ff801b2cf2},
  intrahash = {202b97875a0ca06dba67da3f7febfc86},
  keywords = {AnswerFinder named_entities speech molla_publication},
  pages = {57-65},
  timestamp = {2008-01-29T07:21:37.000+0100},
  title = {Named Entity Recognition in Question Answering of Speech Data},
  url = {http://www.alta.asn.au/events/altw2007/cdrom/index.html},
  volume = 5,
  year = 2007
}

Endnote record

%0 Conference Paper
%1 Moll'a:2007
%A Moll{\'a}, Diego
%A van Zaanen, Menno
%A Cassidy, Steve
%B Proc. ALTW 2007
%D 2007
%E Colineau, Nathalie
%E Dras, Mark
%K 
%P 57-65
%T Named Entity Recognition in Question Answering of Speech Data
%U http://www.alta.asn.au/events/altw2007/cdrom/index.html
%V 5
%X Question answering on speech transcripts (QAst) is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity (NE) recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second (out of three participants) in one of the QAst subtasks.

BibSonomy :: publication ::

Named Entity Recognition in Question Answering of Speech Data

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record