Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/111814
28 Visitors
29 Hits
0 Downloads
- Title
- AnswerFinder at QAst 2007 : named entity recognition for QA on speech transcripts
- Related
- Cross-Language Evaluation Forum Workshop (8th : 2007) (19 - 21 September 2007 : Budapest)
- Related
- Nardi, Alessandro and Peters, Carol. Working Notes for the CLEF 2007 Workshop, 19-21 September, Budapest, Hungary
- Related
- http://www.clef-campaign.org/2007/working_notes/CLEF2007WN-Contents.html
- Publisher
- 2007
- Date
- 2007
- FoR/RFCD Code(s)
-
280103 280205 280206 380202 Information Storage, Retrieval and Management Text Processing Speech Recognition Computational Linguistics
080107 Natural Language Processing
200402 Computational Linguistics
- Author/Creator
- Mollá, Diego
- Author/Creator
- Cassidy, Steve
- Author/Creator
- van Zaanen, Menno
- Description
- Macquarie University’s contribution to the QAst track of CLEF is centered on a study of Named Entity (NE) recognition on speech transcripts, and how such NE recognition 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 types of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning. The machine learning component is a Maximum Entropy classifier and was trained on a development set of the AMI corpus. Problems with scalability of the system and errors of the extracted annotation lead to relatively poor performance in general, though the system was second (out of three participants) in one of the QAst subtasks.
- Description
- 9 page(s)
- Subject Keyword
- 280103 280205 280206 380202 Information Storage, Retrieval and Management Text Processing Speech Recognition Computational Linguistics
- Subject Keyword
- 080107 Natural Language Processing
- Subject Keyword
- 200402 Computational Linguistics
- Subject Keyword
- question answering, speech processing, text processing, computational linguistics
- Subject Keyword
- question answering
- Subject Keyword
- speech transcripts
- Subject Keyword
- named entity recognition
- Resource Type
- conference paper
- Organisation
- Macquarie University. Dept. of Computing
- Identifier
- http://hdl.handle.net/1959.14/111814
- Identifier
- mq-rm-2007002560
- Language
- eng
- Rights
- Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
- Full Text
-
-
List Of Titles
