Our new work extending the previous companion teaching framework for on-line dialogue policy learning has been accepted by the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), which will be held in Copenhagen, Denmark, in September 2017.

Paper + Appendix


The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, effient and economical. But in reality, due to the scarcity of real interaction data, the dialogue system usually grows slowly. Besides, the poor initial dialogue policy easily leads to bad user experience and incurs a failure of attracting users to contribute training data, so that the learning process is unsustainable. To accurately depict this, two quantitative metrics are proposed to assess safety and effiiency issues. For solving the unsustainable learning problem, we proposed a complete companion teaching framework incorporating the guidance from the human teacher. Since the human teaching is expensive, we compared various teaching schemes answering the question how and when to teach, to economically utilize teaching budget, so that make the online learning process affordable.


Runzhe Yang*, Cheng Chang* (equal authorship), Lu Chen, Xiang Zhou and Kai Yu.