Consistent Dialogue Generation with Self-supervised Feature Learning

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generating consistent responses by maintaining certain features related to topics and personas throughout the conversation. Past work has required external supervision that exploits features such as user identities that are often unavailable. In our approach, topic and persona feature extractors are trained using a contrastive training scheme that utilizes the natural structure of dialogue data. We further adopt a feature disentangling loss which, paired with controllable response generation techniques, allows us to promote or demote certain learned topics and persona features. Evaluation results demonstrate the model's ability to capture meaningful topics and persona features. The incorporation of the learned features brings significant improvement in terms of the quality of generated responses on two dialogue datasets.