Automatic evaluation of end-to-end dialog systems with adequacy-fluency metrics.
Luis Fernando D'HaroRafael E. BanchsChiori HoriHaizhou LiPublished in: Comput. Speech Lang. (2019)
Keyphrases
- end to end
- automatic evaluation
- dialog systems
- human judgments
- natural language generation
- natural language
- conversational agents
- natural language interfaces
- human computer
- quality assessment
- human communication
- congestion control
- conversational agent
- artificial intelligence
- semantic relatedness
- human subjects
- machine translation
- ground truth
- image data
- machine learning