CMU system combination via hypothesis selection for WMT'10

Authors:
Almut Silja Hildebrand;Stephan Vogel
Affiliations:
Carnegie Mellon University, Pittsburgh;Carnegie Mellon University, Pittsburgh
Venue:
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Year:
2010

Citing 5
Cited 1

A systematic comparison of various statistical alignment models

Computational Linguistics
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 for building confusion networks with application to machine translation system combination

StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
CMU system combination for WMT'09

StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Machine translation system combination with flexible word ordering

StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation

Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the CMU entry for the system combination shared task at WMT'10. Our combination method is hypothesis selection, which uses information from n-best lists from the input MT systems, where available. The sentence level features used are independent from the MT systems involved. Compared to the baseline we added source-to-target word alignment based features and trained system weights to our feature set. We combined MT systems for French - English and German - English using provided data only.