Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation

Chulun Zhou, Fandong Meng, Jie Zhou, Min Zhang, Hongji Wang, Jinsong Su


Abstract
Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner. Although many previous studies try to incorporate global information into NMT models, there still exist limitations on how to effectively exploit bidirectional global context. In this paper, we propose a Confidence Based Bidirectional Global Context Aware (CBBGCA) training framework for NMT, where the NMT model is jointly trained with an auxiliary conditional masked language model (CMLM). The training consists of two stages: (1) multi-task joint training; (2) confidence based knowledge distillation. At the first stage, by sharing encoder parameters, the NMT model is additionally supervised by the signal from the CMLM decoder that contains bidirectional global contexts. Moreover, at the second stage, using the CMLM as teacher, we further pertinently incorporate bidirectional global context to the NMT model on its unconfidently-predicted target words via knowledge distillation. Experimental results show that our proposed CBBGCA training framework significantly improves the NMT model by +1.02, +1.30 and +0.57 BLEU scores on three large-scale translation datasets, namely WMT’14 English-to-German, WMT’19 Chinese-to-English and WMT’14 English-to-French, respectively.
Anthology ID:
2022.acl-long.206
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2878–2889
Language:
URL:
https://aclanthology.org/2022.acl-long.206
DOI:
10.18653/v1/2022.acl-long.206
Bibkey:
Cite (ACL):
Chulun Zhou, Fandong Meng, Jie Zhou, Min Zhang, Hongji Wang, and Jinsong Su. 2022. Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2878–2889, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation (Zhou et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.206.pdf
Software:
 2022.acl-long.206.software.zip