On the limited memory BFGS method for large scale optimization
Mathematical Programming: Series A and B
BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Minimum error rate training in statistical machine translation
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Minimum risk annealing for training log-linear models
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Consensus training for consensus decoding in machine translation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
BBN system description for WMT10 system combination task
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Findings of the 2011 Workshop on Statistical Machine Translation
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Optimized online rank learning for machine translation
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Batch tuning strategies for statistical machine translation
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Maximum expected BLEU training of phrase and lexicon translation models
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Hi-index | 0.00 |
BBN submitted system combination outputs for Czech-English, German-English, Spanish-English, and French-English language pairs. All combinations were based on confusion network decoding. The confusion networks were built using incremental hypothesis alignment algorithm with flexible matching. A novel bi-gram count feature, which can penalize bi-grams not present in the input hypotheses corresponding to a source sentence, was introduced in addition to the usual decoder features. The system combination weights were tuned using a graph based expected BLEU as the objective function while incrementally expanding the networks to bi-gram and 5-gram contexts. The expected BLEU tuning described in this paper naturally generalizes to hypergraphs and can be used to optimize thousands of weights. The combination gained about 0.5-4.0 BLEU points over the best individual systems on the official WMT11 language pairs. A 39 system multi-source combination achieved an 11.1 BLEU point gain.