BriefGPT.xyz
Jun, 2019
半监督学习的变分时序标记器
Variational Sequential Labelers for Semi-Supervised Learning
HTML
PDF
Mingda Chen, Qingming Tang, Karen Livescu, Kevin Gimpel
TL;DR
介绍了一种基于多任务可变方法的半监督序列标注模型，该模型涵盖了生成模型和判别模型，并探索了一些潜在变量配置方案，能更好地标记数据，使得在8个序列标注数据集中其性能优于标准的顺序基线模型，并且在无标记数据的情况下还有进一步的提升。
Abstract
We introduce a family of multitask variational methods for semi-supervised
sequence labeling
. Our model family consists of a latent-variable generative model and a discriminative labeler. The
generative models
us
→