MANY improvements for WMT'11

Authors:
Loïc Barrault
Affiliations:
LIUM, University of Le Mans, Le Mans, France
Venue:
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Year:
2011

Citing 5
Cited 1

Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Machine translation system combination using ITG-based alignments

HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Incremental hypothesis alignment with flexible matching for building confusion networks: BBN system description for WMT09 system combination task

StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
CONDOR, a new parallel, constrained extension of Powell's UOBYQA algorithm: Experimental results and comparison with the DFO algorithm

Journal of Computational and Applied Mathematics
TER-Plus: paraphrase, semantic, and alignment enhancements to Translation Edit Rate

Machine Translation

Findings of the 2011 Workshop on Statistical Machine Translation

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the development operated into MANY for the 2011 WMT system combination evaluation campaign. Hypotheses from French/English and English/French MT systems were combined with a new version of MANY, an open source system combination software based on confusion networks decoding currently developed at LIUM. MANY has been updated in order to optimize decoder parameters with MERT, which proves to find better weights. The system combination yielded significant improvements in BLEU score when applied on system combination data from two languages.