Automatic evaluation of end-to-end dialog systems with adequacy-fluency metrics
Computer Speech & Language(2019)
摘要
•Automatic metric for evaluating natural language generated sentences for dialog systems.•Integration of adequacy and fluency information to jointly evaluate semantic and syntactic information.•Higher correlation (up to 12.8%) with human evaluations than the best current objective metrics at a system and sentence level.
更多查看译文
关键词
Automatic evaluation metrics,dialog systems,DSTC,adequacy and fluency
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要