FFAEval: Evaluating Dialogue System via Free-For-All Ranking.
Zeyao MaZijun YaoJing ZhangJifan YuXiaohan ZhangJuanzi LiJie TangPublished in: EMNLP (Findings) (2023)
Keyphrases
- dialogue system
- human computer
- dialogue management
- natural language
- natural language generation
- spoken dialogue systems
- human robot
- natural language understanding
- linguistic knowledge
- mixed initiative
- ranking algorithm
- learning to rank
- tutorial dialogue
- spoken language
- language understanding
- web search
- human users
- dialogue manager
- ranking functions
- user model
- training data
- knowledge base
- data mining