Learning to Translate in Real-time with Neural Machine Translation
This addresses the problem of low-latency translation for users needing real-time communication, representing an incremental improvement with novel method integration.
The paper tackles the challenge of real-time simultaneous translation by proposing a neural machine translation framework where an agent learns when to translate from interaction with a pre-trained environment, achieving efficacy in experiments against state-of-the-art baselines on two language pairs.
Translating in real-time, a.k.a. simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.