arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.04738cs.CLstat.ML
收藏

一种高效的神经网络机器翻译

An Efficient Character-Level Neural Machine Translation

Shanghai Jiao Tong University(上海交通大学)

Shenjian Zhao, Zhihua Zhang

摘要:

神经机器翻译旨在构建一个单一的大型神经网络,可以训练它以最大限度地提高翻译性能。具有注意力机制的编码器-解码器架构在英法翻译任务上实现了与现有的最先进的基于短语的系统相当的翻译性能。然而,大词汇量的使用成为训练和提高性能的瓶颈。在本文中,我们提出了一个有效的架构,训练一个深字符级神经机器翻译通过引入一个抽取器和一个抽取器。抽取器用于在编码之前对源序列进行采样,而采样器用于在解码之后对源序列进行重采样。这种深度模型有两大优势。它从根本上避免了大词汇量的问题;同时,它在训练中比传统的基于字符的模型更快,更节省内存。更有趣的是,我们的模型能够像人类一样翻译拼写错误的单词。

英文摘要:

Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to the existing state-of-the-art phrase-based systems on the task of English-to-French translation. However, the use of large vocabulary becomes the bottleneck in both training and improving the performance. In this paper, we propose an efficient architecture to train a deep character-level neural machine translation by introducing a decimator and an interpolator. The decimator is used to sample the source sequence before encoding while the interpolator is used to resample after decoding. Such a deep model has two major advantages. It avoids the large vocabulary issue radically; at the same time, it is much faster and more memory-efficient in training than conventional character-based models. More interestingly, our model is able to translate the misspelled word like human beings.

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。

↑