Generating Stylistically Consistent Dialog Responses with Transfer Learning

IJCNLP 2017 · Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, Kentaro Inui ·

We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain.