We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention for character-level machine translation. We develop a model that plans ahead when it computes alignments between the source and target sequences, constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan. This mechanism is inspired by the strategic attentive reader and writer (STRAW) model. Our proposed model is end-to-end trainable with fully differentiable operations. We show that it outperforms a strong baseline on three character-level decoder neural machine translation on WMT'15 corpus. Our analysis demonstrates that our model can compute qualitatively intuitive alignments and achieves superior performance with fewer parameters.

研究在字符级机器翻译中将规划机制与显式对齐的编码器-解码器架构相结合，开发了一种计划先行的模型，该模型可以计算源序列和目标序列之间的对齐，并构建一个建议的未来对齐矩阵和一个决策向量以确定是否遵循或重新计算计划。该机制受到了战略关注读者和写作者（STRAW）模型的启发，并通过WMT'15语料库上字符级解码器神经机器翻译的三个任务表现优异。我们的分析表明，我们的模型可以计算出具有定性直观性的对齐，并且使用更少的参数可以实现卓越的性能。

计划、关注、生成：具备解码器规划功能的汉字级神经机器翻译