Named entity recognition in question answering of speech data

Diego Mollá, Menno van Zaanen, Steve Cassidy

Research output: Contribution to journalConference paperpeer-review

63 Downloads (Pure)

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 questionanswering 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.
Original languageEnglish
Pages (from-to)57-65
Number of pages9
JournalProceedings of the 2007 Australasian Language Technology Workshop
Publication statusPublished - 2007
EventAustralasian Language Technology Workshop (2007) - Melbourne
Duration: 10 Dec 200711 Dec 2007

Keywords

  • named entity recognition
  • question answering
  • speech processing
  • text processing

Fingerprint

Dive into the research topics of 'Named entity recognition in question answering of speech data'. Together they form a unique fingerprint.

Cite this