Simple and Effective Noisy Channel Modeling for Neural Machine Translation

Kyra Yee, Yann Dauphin, Michael Auli


Abstract
Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. This makes decoding decisions based on partial source prefixes even though the full source is available. We pursue an alternative approach based on standard sequence to sequence models which utilize the entire source. These models perform remarkably well as channel models, even though they have neither been trained on, nor designed to factor over incomplete target sentences. Experiments with neural language models trained on billions of words show that noisy channel models can outperform a direct model by up to 3.2 BLEU on WMT’17 German-English translation. We evaluate on four language-pairs and our channel models consistently outperform strong alternatives such right-to-left reranking models and ensembles of direct models.
Anthology ID:
D19-1571
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5696–5701
Language:
URL:
https://aclanthology.org/D19-1571
DOI:
10.18653/v1/D19-1571
Bibkey:
Cite (ACL):
Kyra Yee, Yann Dauphin, and Michael Auli. 2019. Simple and Effective Noisy Channel Modeling for Neural Machine Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5696–5701, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Simple and Effective Noisy Channel Modeling for Neural Machine Translation (Yee et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1571.pdf
Attachment:
 D19-1571.Attachment.pdf
Code
 pytorch/fairseq