DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation

2Citations
Citations of this article
14Readers
Mendeley users who have this article in their library.

Abstract

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease the number of required steps to reach a certain translation quality. The distilled model enjoys the computational benefits of early iterations while preserving the enhancements from several iterative steps. DiMS relies on two models namely student and teacher. The student is optimized to predict the output of the teacher after multiple decoding steps while the teacher follows the student via a slow-moving average. The moving average keeps the teacher's knowledge updated and enhances the quality of the labels provided by the teacher. During inference, the student is used for translation and no additional computation is added. We verify the effectiveness of DiMS on various models obtaining 7.8 and 12.9 BLEU points improvements in single-step translation accuracy on distilled and raw versions of WMT'14 De-En. Full code for this work is available here: https://github.com/layer6ai-labs/DiMS.

Cite

CITATION STYLE

APA

Norouzi, S., Hosseinzadeh, R., Pérez, F., & Volkovs, M. (2023). DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 8538–8553). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.findings-acl.542

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free