Using Collaborative Filtering to Predict User Utterances in Dialogue
msra(2010)
摘要
This paper proposes using collaborative filtering, a technique for using other users' information to model the behavior of a certain user, to predict users' evaluative expressions for entities in dialogue. Previous studies have found that inducing users' empathic utterances towards systems can improve user satisfaction. Predicting what users may utter and communicating this information in advance would make it easy for users to show empathy, leading to possible improvement in the quality of dialogue. Experimental results show that our approach, which uses the similarity users and entities, can significantly improve the predic- tion of evaluative expressions compared to a baseline that ignores such similarity.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络