Prediction Improves Simultaneous Neural Machine Translation
Prediction Improves Simultaneous Neural Machine Translation
复制标题
DOI：
10.18653/v1/d18-1337
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Ashkan Alinejad;Maryam Siahbani;Anoop Sarkar
中科院分区：
文献类型：
--
作者：
Ashkan Alinejad;Maryam Siahbani;Anoop Sarkar
同声翻译的目的是在保证翻译质量的同时，尽量减少阅读输入和增量输出之间的延迟。我们提出了一种新的通用预测动作，它可以预测输入中的未来单词，以提高同声翻译的质量并最大限度地减少延迟。我们使用带有新颖奖励函数的强化学习来训练这个智能体。与没有预测的基于agent的同声翻译系统相比，我们的具有预测的agent具有更好的翻译质量和更小的延迟。
Simultaneous speech translation aims to maintain translation quality while minimizing the delay between reading input and incrementally producing the output. We propose a new general-purpose prediction action which predicts future words in the input to improve quality and minimize delay in simultaneous translation. We train this agent using reinforcement learning with a novel reward function. Our agent with prediction has better translation quality and less delay compared to an agent-based simultaneous translation system without prediction.