A discriminative framework for bilingual word alignment

A discriminative framework for bilingual word alignment (2005)

by Robert C. Moore

Venue:	In Proceedings of HLT-EMNLP
Citations:	53 - 1 self

Datum	Value	Source
TITLE	A discriminative framework for bilingual word alignment	INFERENCE
AUTHOR NAME	Robert C. Moore	SVM HeaderParse 0.2
AUTHOR AFFIL	Microsoft Research; One Microsoft Way	SVM HeaderParse 0.2
AUTHOR ADDR	Redmond, WA 98052	SVM HeaderParse 0.2
ABSTRACT	Bilingual word alignment forms the foundation of most approaches to statistical machine translation. Current word alignment methods are predominantly based on generative models. In this paper, we demonstrate a discriminative approach to training simple word alignment models that are comparable in accuracy to the more complex generative models normally used. These models have the the advantages that they are easy to add features to and they allow fast optimization of model parameters using small amounts of annotated data. 1	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	In Proceedings of HLT-EMNLP	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	81--88	INFERENCE
CITATIONS	13 found	ParsCit 1.0