BriefGPT.xyz
Apr, 2017
文本分类的对抗多任务学习
Adversarial Multi-task Learning for Text Classification
HTML
PDF
Pengfei Liu, Xipeng Qiu, Xuanjing Huang
TL;DR
本文提出了一个基于对抗学习的多任务学习框架,在16个文本分类任务上的实验结果表明了该方法的优势,并证明了模型学习到的共享知识可以作为现成的知识轻松迁移到新的任务中。
Abstract
neural network
models have shown their promising opportunities for
multi-task learning
, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing appro
→