A Deep Reinforcement Learning Based Multi-Step Coarse to Fine Question Answering (MSCQA) System.
Yu WangHongxia JinPublished in: AAAI (2019)
Keyphrases
- coarse to fine
- question answering
- multi step
- reinforcement learning
- multiscale
- multiresolution
- dynamic programming
- image registration
- object detection
- question classification
- named entities
- natural language processing
- information extraction
- natural language
- information retrieval
- cross language
- passage retrieval
- machine learning
- natural language questions
- knn
- syntactic information
- learning process
- qa clef
- image analysis
- feature selection
- semantic roles
- candidate answers
- neural network
- answer extraction
- data sets