Speculative Beam Search for Simultaneous Translation

Renjie Zheng, Mingbo Ma, Baigong Zheng, Liang Huang


Abstract
Beam search is universally used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial, where output words are committed on the fly. In particular, the recently proposed wait-k policy (Ma et al., 2018) is a simple and effective method that (after an initial wait) commits one output word on receiving each input word, making beam search seemingly inapplicable. To address this challenge, we propose a new speculative beam search algorithm that hallucinates several steps into the future in order to reach a more accurate decision by implicitly benefiting from a target language model. This idea makes beam search applicable for the first time to the generation of a single word in each step. Experiments over diverse language pairs show large improvement compared to previous work.
Anthology ID:
D19-1144
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
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1395–1402
Language:
URL:
https://aclanthology.org/D19-1144
DOI:
10.18653/v1/D19-1144
Bibkey:
Cite (ACL):
Renjie Zheng, Mingbo Ma, Baigong Zheng, and Liang Huang. 2019. Speculative Beam Search for Simultaneous 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 1395–1402, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Speculative Beam Search for Simultaneous Translation (Zheng et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1144.pdf
Attachment:
 D19-1144.Attachment.pdf