Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation

Huanran Zheng, Wei Zhu, Pengfei Wang, Xiaoling Wang

Abstract
Non-autoregressive translation (NAT) model achieves a much faster inference speed than the autoregressive translation (AT) model because it can simultaneously predict all tokens during inference. However, its translation quality suffers from degradation compared to AT. And existing NAT methods only focus on improving the NAT model’s performance but do not fully utilize it. In this paper, we propose a simple but effective method called “Candidate Soups,” which can obtain high-quality translations while maintaining the inference speed of NAT models. Unlike previous approaches that pick the individual result and discard the remainders, Candidate Soups (CDS) can fully use the valuable information in the different candidate translations through model uncertainty. Extensive experiments on two benchmarks (WMT’14 EN–DE and WMT’16 EN–RO) demonstrate the effectiveness and generality of our proposed method, which can significantly improve the translation quality of various base models. More notably, our best variant outperforms the AT model on three translation tasks with 7.6× speedup.
Anthology ID:
2022.emnlp-main.318
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4811–4823
Language:
URL:
https://aclanthology.org/2022.emnlp-main.318
DOI:
10.18653/v1/2022.emnlp-main.318
Bibkey:
Cite (ACL):
Huanran Zheng, Wei Zhu, Pengfei Wang, and Xiaoling Wang. 2022. Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4811–4823, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation (Zheng et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.318.pdf
PDF Search