Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
This addresses the need for AI dialogue systems to produce engaging, personalized responses while maintaining factual accuracy, though it is an incremental advancement in combining style and knowledge.
The paper tackles the problem of generating stylized responses in knowledge-grounded dialogues without supervised data, proposing a disentangled template rewriting method that significantly improves over prior stylized dialogue methods and matches state-of-the-art knowledge-grounded dialogue performance.
Current Knowledge-Grounded Dialogue Generation (KDG) models specialize in producing rational and factual responses. However, to establish long-term relationships with users, the KDG model needs the capability to generate responses in a desired style or attribute. Thus, we study a new problem: Stylized Knowledge-Grounded Dialogue Generation (SKDG). It presents two challenges: (1) How to train a SKDG model where no <context, knowledge, stylized response> triples are available. (2) How to cohere with context and preserve the knowledge when generating a stylized response. In this paper, we propose a novel disentangled template rewriting (DTR) method which generates responses via combing disentangled style templates (from monolingual stylized corpus) and content templates (from KDG corpus). The entire framework is end-to-end differentiable and learned without supervision. Extensive experiments on two benchmarks indicate that DTR achieves a significant improvement on all evaluation metrics compared with previous state-of-the-art stylized dialogue generation methods. Besides, DTR achieves comparable performance with the state-of-the-art KDG methods in standard KDG evaluation setting.