CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection.
Chongyang TaoJiazhan FengTao ShenChang LiuJuntao LiXiubo GengDaxin JiangPublished in: ACL (1) (2023)
Keyphrases
- cooperative
- training set
- high quality
- mixed initiative
- data mining
- training examples
- real time
- computationally efficient
- online learning
- multi agent systems
- cooperative learning
- training phase
- game theory
- training samples
- hidden markov models
- reinforcement learning
- case study
- website
- learning algorithm
- genetic algorithm
- neural network