arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.04525cs.CL
收藏

神经机器翻译的离散结构规划

Discrete Structural Planning for Neural Machine Translation

The University of Tokyo(东京大学)

Raphael Shu, Hideki Nakayama

摘要:

结构规划对于生成长句很重要,这是当前语言生成模型中缺少的部分。在这项工作中,我们在神经机器翻译中添加了一个规划阶段,以控制输出句子的粗略结构。该模型首先生成一些规划器代码,然后预测实际输出的话,他们的条件。学习代码以捕获目标句子的粗略结构。为了获得代码,我们设计了一个具有离散化瓶颈的端到端神经网络,它预测目标句子的简化词性标记。实验表明,通过提前规划,翻译性能得到了普遍提高.我们还发现,具有不同结构的翻译可以通过操纵的计划者代码。

英文摘要:

Structural planning is important for producing long sentences, which is a missing part in current language generation models. In this work, we add a planning phase in neural machine translation to control the coarse structure of output sentences. The model first generates some planner codes, then predicts real output words conditioned on them. The codes are learned to capture the coarse structure of the target sentence. In order to obtain the codes, we design an end-to-end neural network with a discretization bottleneck, which predicts the simplified part-of-speech tags of target sentences. Experiments show that the translation performance are generally improved by planning ahead. We also find that translations with different structures can be obtained by manipulating the planner codes.

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。

↑