DeepAI AI Chat
Log In Sign Up

Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy

by   Zhengxin Yang, et al.

Simultaneous translation, which starts translating each sentence after receiving only a few words in source sentence, has a vital role in many scenarios. Although the previous prefix-to-prefix framework is considered suitable for simultaneous translation and achieves good performance, it still has two inevitable drawbacks: the high computational resource costs caused by the need to train a separate model for each latency k and the insufficient ability to encode information because each target token can only attend to a specific source prefix. We propose a novel framework that adopts a simple but effective decoding strategy which is designed for full-sentence models. Within this framework, training a single full-sentence model can achieve arbitrary given latency and save computational resources. Besides, with the competence of the full-sentence model to encode the whole sentence, our decoding strategy can enhance the information maintained in the decoded states in real time. Experimental results show that our method achieves better translation quality than baselines on 4 directions: Zh→En, En→Ro and En↔De.


page 1

page 2

page 3

page 4


STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency

Simultaneous translation, which translates sentences before they are fin...

Improving Simultaneous Translation with Pseudo References

Simultaneous translation is vastly different from full-sentence translat...

Opportunistic Decoding with Timely Correction for Simultaneous Translation

Simultaneous translation has many important application scenarios and at...

Data-Driven Adaptive Simultaneous Machine Translation

In simultaneous translation (SimulMT), the most widely used strategy is ...

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation

Simultaneous machine translation (SiMT) starts its translation before re...

Glancing Future for Simultaneous Machine Translation

Simultaneous machine translation (SiMT) outputs translation while readin...

Learn to Use Future Information in Simultaneous Translation

Simultaneous neural machine translation (briefly, NMT) has attracted muc...