arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.09863cs.CL
收藏

快速神经机器翻译实现

Fast Neural Machine Translation Implementation

University of Edinburgh(爱丁堡大学);Adam Mickiewicz University(亚当·密茨凯维奇大学);Tilde Universitat d’Alacant(阿利坎特大学(Tilde))

Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, Kenneth Heafield

摘要:

本文介绍了爱丁堡大学、亚当密茨凯维奇大学、蒂尔德大学和阿利坎特大学的成员在神经机器翻译和生成研讨会上提交的GPU效率跟踪报告。我们专注于在神经机器翻译的快速推理引擎Amun中实现的循环深度学习模型的有效实现。我们通过一个高效的mini-square算法,并通过融合softmax操作与k-best提取算法来提高性能。使用Amun的提交在GPU效率跟踪中排名第一,第二和第三。

英文摘要:

This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.

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。

↑