Learning Structured Representation for Text Classification ...

Learning Structured Representation for Text Classification via Reinforcement Learning Tianyang Zhang? , Minlie Huang?, , Li Zhao . ? Tsinghua National Laboratory for Information Science and Technology Dept. of Computer Science and Technology, Tsinghua University, Beijing 100084, PR China . Microsoft Research Asia . Corresponding Author: (Minlie Huang). Abstract and recursive autoencoders (Socher et al. 2013; 2011; Qian et al. 2015) use pre-specified parsing trees to build Structured Representation Learning is a fundamental problem in natural representations.

sions, which can be addressed by policy gradient RL. Results show that our method can learn task-friendly representation-s by identifying important words or task-relevant structures without explicit structure annotations, and thus yields com-petitive performance. Introduction Representation learning is a fundamental problem in AI,

Loading..

Tags:

  Policy, Derating, Policy gradient

Information

Related search queries