Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems.
Vitou PhyYang ZhaoAkiko AizawaPublished in: COLING (2020)
Keyphrases
- open domain
- dialogue system
- evaluation metrics
- information extraction
- precision and recall
- natural language
- question answering
- spoken dialogue systems
- average precision
- question answering systems
- learning to rank
- human users
- tutorial dialogue
- evaluation measures
- natural language processing
- user model
- unknown words
- machine learning
- dialogue games
- intelligent agents
- semi supervised
- user interface
- multi agent
- information retrieval