Abstract

Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform simple fixed policies. We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies. Experiments on Chinese -> English and German -> English show that our adaptive policies can outperform fixed ones by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses the BLEU score of full-sentence translation in the greedy mode (and very close to beam mode), but with much lower latency.

Highlights

  • Simultaneous translation (ST) aims to provide good translation quality while keeping the latency of translation process as low as possible

  • If the Neural machine translation (NMT) model follows a wait-k policy, and predicts the most likely token with probability higher than the threshold ρk, we consider the model is confident on this prediction, and choose WRITE action; otherwise, we choose READ action

  • We test three different cases: (1) single, where for each policy we apply the corresponding model that trained with the same policy; (2) ensemble top-3, where for each policy we apply the ensemble of 3 models that achieve the highest BLEU scores with that policy on dev set; (3) ensemble all, where we apply the ensemble of all 10 models for each policy

Read more

Summary

Introduction

Simultaneous translation (ST) aims to provide good translation quality while keeping the latency of translation process as low as possible. The wait-k policy by Ma et al (2019) first chooses k READ actions, and chooses WRITE and READ alternatively This kind of policies do not utilize the context information and can be either too aggressive or too conservative in different cases. It is obvious that this kind of policies is more desirable for ST than the fixed ones, and different methods are explored to achieve an adaptive policy The majority of such methods (Grissom II et al, 2014; Cho and Esipova, 2016; Gu et al, 2017; Alinejad et al, 2018; Zheng et al, 2019a) are based on full-sentence translation models, which may be simple to use but cannot outperform fixed policies applied with “genuinely simultaneous” models trained for ST (Ma et al, 2019). Compared with full-sentence translation, our method achieves higher BLEU scores than greedy search but with much lower latency, and is close to the results from beam search

Preliminaries
Obtaining an Adaptive Policy
Ensemble of Wait-k Models
Conclusions
A Appendices
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.