RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees.
Tengxiao LiuQipeng GuoXiangkun HuYue ZhangXipeng QiuZheng ZhangPublished in: EMNLP (2022)
Keyphrases
- reinforcement learning
- question answering
- function approximation
- decision trees
- logic programming
- np complete
- machine learning
- open domain
- textual entailment
- model free
- robotic control
- state space
- tree structure
- answer validation
- question classification
- tree models
- tree structures
- dynamic programming
- learning process
- data structure
- textual entailment recognition
- recognizing textual entailment
- qa clef
- optimal policy
- probabilistic model
- learning algorithm