An End-To-End Actor-Critic-Based Neural Coreference Resolution System.
Yu WangYilin ShenHongxia JinPublished in: ICASSP (2021)
Keyphrases
- end to end
- coreference resolution
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- network architecture
- approximate dynamic programming
- neuro fuzzy
- temporal difference
- natural language processing
- gradient method
- noun phrases
- neural network
- reinforcement learning algorithms
- relation extraction
- function approximation
- policy iteration
- state space
- hidden variables
- active learning
- generative model
- domain specific