A Translation Model for Sentence Retrieval

A Translation Model for Sentence Retrieval (2005)

by Vanessa Murdock , W. Bruce Croft

Venue:	in Proceedings of the Conference on Human Language Technologies and Empirical Methods in Natural Language Processing (HLT/EMNLP
Citations:	19 - 5 self

Datum	Value	Source
TITLE	A Translation Model for Sentence Retrieval	SVM HeaderParse 0.2
AUTHOR NAME	Vanessa Murdock	SVM HeaderParse 0.2
AUTHOR AFFIL	Center for Intelligent Information Retrieval; Computer Science Department; University of Massachusetts	SVM HeaderParse 0.2
AUTHOR ADDR	Amherst, MA 01003	SVM HeaderParse 0.2
AUTHOR NAME	W. Bruce Croft	SVM HeaderParse 0.2
AUTHOR AFFIL	Center for Intelligent Information Retrieval; Computer Science Department; University of Massachusetts	SVM HeaderParse 0.2
AUTHOR ADDR	Amherst, MA 01003	SVM HeaderParse 0.2
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. 1	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	in Proceedings of the Conference on Human Language Technologies and Empirical Methods in Natural Language Processing (HLT/EMNLP	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	684--691	INFERENCE
CITATIONS	15 found	ParsCit 1.0