BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for 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
Improving alignments for better confusion networks for combining machine translation systems
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Indirect-HMM-based hypothesis alignment for combining outputs from machine translation systems
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
Fluency, adequacy, or HTER?: exploring different human judgments with a tunable MT metric
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Findings of the 2009 workshop on statistical machine translation
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
BBN system description for WMT10 system combination task
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Combining unsupervised and supervised alignments for MT: an empirical study
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Expected BLEU training for graphs: BBN system description for WMT11 system combination task
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Review of hypothesis alignment algorithms for MT system combination via confusion network decoding
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Hi-index | 0.01 |
This paper describes the incremental hypothesis alignment algorithm used in the BBN submissions to the WMT09 system combination task. The alignment algorithm used a sentence specific alignment order, flexible matching, and new shift heuristics. These refinements yield more compact confusion networks compared to using the pair-wise or incremental TER alignment algorithms. This should reduce the number of spurious insertions in the system combination output and the system combination weight tuning converges faster. System combination experiments on the WMT09 test sets from five source languages to English are presented. The best BLEU scores were achieved by combing the English outputs of three systems from all five source languages.