Semi-Autoregressive Neural Machine Translation

Chunqi Wang, Ji Zhang, Haiqing Chen


Abstract
Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation — the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus are able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show that the SAT achieves a good balance between translation quality and decoding speed. On WMT’14 English-German translation, the SAT achieves 5.58× speedup while maintaining 88% translation quality, significantly better than the previous non-autoregressive methods. When produces two words at each time step, the SAT is almost lossless (only 1% degeneration in BLEU score).
Anthology ID:
D18-1044
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
479–488
Language:
URL:
https://aclanthology.org/D18-1044
DOI:
10.18653/v1/D18-1044
Bibkey:
Cite (ACL):
Chunqi Wang, Ji Zhang, and Haiqing Chen. 2018. Semi-Autoregressive Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 479–488, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Semi-Autoregressive Neural Machine Translation (Wang et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/D18-1044.pdf
Code
 chqiwang/sa-nmt
Data
WMT 2014