arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.02005cs.CL
收藏

记忆增强神经机器翻译

Memory-augmented Neural Machine Translation

Center for Speech and Language Technologies, RIIT, Tsinghua University(清华大学信息技术研究院语音与语言技术中心);Huilan Corporation(慧兰公司);Beijing University of Posts and Telecommunications(北京邮电大学)

Yang Feng, Shiyue Zhang, Andi Zhang, Dong Wang, Andrew Abel

摘要:

神经机器翻译(NMT)在最近取得了显著的成功,然而,人们也普遍认识到,这种方法在处理不频繁的单词和单词对方面存在局限性。本文提出了一种新的内存增强NMT(M-NMT)架构,它存储有关如何在内存中翻译单词(通常是不经常遇到的单词)的知识,然后利用它们来辅助神经模型。我们使用这种记忆机制,结合从传统的统计机器翻译系统和NMT系统学习的规则学习的知识,并提出了一个解决方案的词汇表外(OOV)的话,基于这个框架。我们在两个汉英翻译任务上的实验表明,M-NMT架构在这两个任务上的表现分别优于NMT基线的$9.0$和$2.7$ BLEU点。此外,我们发现,与竞争性方法相比,这种架构导致更有效的OOV治疗。

英文摘要:

Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memory-augmented NMT (M-NMT) architecture, which stores knowledge about how words (usually infrequently encountered ones) should be translated in a memory and then utilizes them to assist the neural model. We use this memory mechanism to combine the knowledge learned from a conventional statistical machine translation system and the rules learned by an NMT system, and also propose a solution for out-of-vocabulary (OOV) words based on this framework. Our experiments on two Chinese-English translation tasks demonstrated that the M-NMT architecture outperformed the NMT baseline by $9.0$ and $2.7$ BLEU points on the two tasks, respectively. Additionally, we found this architecture resulted in a much more effective OOV treatment compared to competitive methods.

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。

↑