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 1903.07402cs.CL
收藏

Neutron:Transformer翻译模型及其变体的实现

Neutron: An Implementation of the Transformer Translation Model and its Variants

Saarland University(萨尔兰大学);DFKI(德国人工智能研究中心);China Mobile Online Services(中国移动在线服务有限公司)

Hongfei Xu, Qiuhui Liu

摘要:

与递归seq2seq模型相比,Transformer翻译模型更容易并行化,并提供更好的性能,这使得它在工业和研究社区中很受欢迎。我们在这项工作中实现了中子,包括Transformer模型及其最近研究的几个变体。它经过高度优化,易于修改,并在保持可读性的同时提供具有有趣功能的可比性能。

英文摘要:

The Transformer translation model is easier to parallelize and provides better performance compared to recurrent seq2seq models, which makes it popular among industry and research community. We implement the Neutron in this work, including the Transformer model and its several variants from most recent researches. It is highly optimized, easy to modify and provides comparable performance with interesting features while keeping readability.

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。

↑