A translation model for sentence retrieval

Murdock, V and Croft, B 2005, 'A translation model for sentence retrieval', in Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), Vancouver, Canada, 6-8 October 2005, pp. 684-691.


Document type: Conference Paper
Collection: Conference Papers

Title A translation model for sentence retrieval
Author(s) Murdock, V
Croft, B
Year 2005
Conference name Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)
Conference location Vancouver, Canada
Conference dates 6-8 October 2005
Proceedings title Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)
Publisher Association for Computational Linguistics (ACL)
Place of publication United States
Start page 684
End page 691
Total pages 8
Abstract In this work we propose a translation model for monolingual sentence retrieval. We propose four methods for constructing a parallel corpus. Of the four methods proposed, a lexicon learned from a bilingual Arabic- English corpus aligned at the sentence level performs best, significantly improving results over the query likelihood baseline. Further, we demonstrate that smoothing from the local context of the sentence improves retrieval over the query likelihood baseline.
Subjects Information Systems not elsewhere classified
Copyright notice © 2005 Association for Computational Linguistics
Versions
Version Filter Type
Access Statistics: 91 Abstract Views  -  Detailed Statistics
Created: Tue, 19 Feb 2013, 12:43:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us