Model combination for machine translation

Model combination for machine translation (2010)

by John Denero , Shankar Kumar , Ciprian Chelba , Franz Och

Venue:	In Proceedings NAACL-HLT
Citations:	4 - 0 self

Datum	Value	Source
TITLE	Model combination for machine translation	INFERENCE
AUTHOR NAME	John Denero	SVM HeaderParse 0.2
AUTHOR AFFIL	UC Berkeley	SVM HeaderParse 0.2
AUTHOR NAME	Shankar Kumar	SVM HeaderParse 0.2
AUTHOR AFFIL	Google, Inc.	SVM HeaderParse 0.2
AUTHOR NAME	Ciprian Chelba	SVM HeaderParse 0.2
AUTHOR AFFIL	Google, Inc.	SVM HeaderParse 0.2
AUTHOR NAME	Franz Och	SVM HeaderParse 0.2
AUTHOR AFFIL	Google, Inc.	SVM HeaderParse 0.2
ABSTRACT	Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combination, a method that integrates consensus decoding and system combination into a unified, forest-based technique. Our approach makes few assumptions about the underlying component models, enabling us to combine systems with heterogenous structure. Unlike most system combination techniques, we reuse the search space of component models, which entirely avoids the need to align translation hypotheses. Despite its relative simplicity, model combination improves translation quality over a pipelined approach of first applying consensus decoding to individual systems, and then applying system combination to their output. We demonstrate BLEU improvements across data sets and language pairs in large-scale experiments. 1	SVM HeaderParse 0.2
YEAR	2010	INFERENCE
VENUE	In Proceedings NAACL-HLT	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	21 found	ParsCit 1.0