arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.05087cs.CLcs.NE
收藏

计划,参与,生成:解码器中带有规划的机器人级神经机器翻译

Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder

University of Montreal(蒙特利尔大学);Microsoft Maluuba(微软 Maluuba)

Caglar Gulcehre, Francis Dutil, Adam Trischler, Yoshua Bengio

摘要:

我们研究的规划机制集成到一个编码器-解码器架构与字符级机器翻译的显式对齐。我们开发了一个模型,在计算源序列和目标序列之间的比对时提前计划,构建拟议的未来比对矩阵和控制是否遵循或重新计算计划的承诺向量。这一机制的灵感来自于策略性的专注读者和作者(StrategicAttentive Reader and Writer,缩写为ESTA)模型。我们提出的模型是端到端可训练的,具有完全可区分的操作。我们证明了它在WMT'15语料库上的三个字符级解码器神经机器翻译上的性能优于强基线。我们的分析表明,我们的模型可以计算定性直观的路线,并实现了更少的参数优越的性能。

英文摘要:

We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑