BriefGPT.xyz
Apr, 2022
$ extit{latent}$-GLAT：关注潜在变量的并行文本生成技术
$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation
HTML
PDF
Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian...
TL;DR
本文提出了一种使用离散潜在变量和课程学习技术的平行文本生成方法，不需要使用自回归模型训练即可解决数据集中的多模态问题，并在实验中取得优秀的表现，进一步拓宽了平行解码范式的应用场景。
Abstract
Recently,
parallel text generation
has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its generation quality, they still need the help of an
→