arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07905cs.CL
收藏

用于非自回归神经机器翻译的扫视Transformer

Glancing Transformer for Non-Autoregressive Neural Machine Translation

Shanghai Jiao Tong University(上海交通大学);ByteDance AI Lab(字节跳动人工智能实验室);Nanjing University(南京大学)

Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei Li

摘要:

非自回归神经机器翻译(NAT)的最新研究工作旨在通过并行解码提高效率而不牺牲质量。然而,现有的NAT方法要么不如Transformer,要么需要多个解码通道,导致加速降低。我们提出了扫视语言模型(GLM),一种方法来学习单词的相互依赖性的单通道并行生成模型。借助GLM,我们开发了用于机器翻译的Glancing Transformer(GLAT)。仅使用单遍并行解码,GLAT能够以8-15倍的加速生成高质量的翻译。在多个WMT语言方向上的实验表明,GLAT优于所有以前的单通道非自回归方法,并且几乎与Transformer相当,将差距缩小到0.25-0.9 BLEU点。

英文摘要:

Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the Glancing Language Model (GLM), a method to learn word interdependency for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8-15 times speedup. Experiments on multiple WMT language directions show that GLAT outperforms all previous single pass non-autoregressive methods, and is nearly comparable to Transformer, reducing the gap to 0.25-0.9 BLEU points.

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。

↑