A hierarchical self-attentive neural extractive summarizer via reinforcement learning (HSASRL).
Farida MohsenJiayang WangKamal Al-SabahiPublished in: Appl. Intell. (2020)
Keyphrases
- reinforcement learning
- multi document summarization
- automatic summarization
- text summarization
- fitted q iteration
- network architecture
- state space
- hierarchical reinforcement learning
- function approximation
- hierarchical structure
- coarse to fine
- reinforcement learning algorithms
- focus of attention
- model free
- document summarization
- visual attention
- markov decision processes
- dynamic programming
- sensory inputs
- lexical chains
- automatic text summarization
- biologically inspired
- language independent
- neural network
- hierarchical clustering
- vision system
- natural language processing
- keywords
- learning algorithm