TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
This addresses the issue of uncontrollable and unrelated responses in end-to-end dialogue systems, though it appears incremental as it builds on existing methods like GPT2 and BERT.
The paper tackles the problem of generating topic-aware responses in multi-turn dialogues by proposing a joint framework that simultaneously learns topic prediction and response generation, achieving new state-of-the-art performance in response generation.
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses. Previous research has either predicted the topic first and then generated the relevant response, or simply applied the attention mechanism to all topics, ignoring the joint distribution of the topic prediction and response generation models and resulting in uncontrollable and unrelated responses. In this paper, we propose a joint framework with a topic refinement mechanism to learn these two tasks simultaneously. Specifically, we design a three-pass iteration mechanism to generate coarse response first, then predict corresponding topics, and finally generate refined response conditioned on predicted topics. Moreover, we utilize GPT2DoubleHeads and BERT for the topic prediction task respectively, aiming to investigate the effects of joint learning and the understanding ability of GPT model. Experimental results demonstrate that our proposed framework achieves new state-of-the-art performance at response generation task and the great potential understanding capability of GPT model.