Unified Knowledge Prompt Pre-training for Customer Service Dialogues
This work addresses the challenge of integrating weakly-supervised expert knowledge into dialogue systems for customer service, though it appears incremental as it builds on existing pre-training models.
The paper tackles the problem of customer service dialogue bots needing to handle multiple tasks like domain classification, intent understanding, and response generation by proposing a unified knowledge prompt pre-training framework called UFA, which achieves significant improvements on NLU and NLG benchmarks.
Dialogue bots have been widely applied in customer service scenarios to provide timely and user-friendly experience. These bots must classify the appropriate domain of a dialogue, understand the intent of users, and generate proper responses. Existing dialogue pre-training models are designed only for several dialogue tasks and ignore weakly-supervised expert knowledge in customer service dialogues. In this paper, we propose a novel unified knowledge prompt pre-training framework, UFA (\textbf{U}nified Model \textbf{F}or \textbf{A}ll Tasks), for customer service dialogues. We formulate all the tasks of customer service dialogues as a unified text-to-text generation task and introduce a knowledge-driven prompt strategy to jointly learn from a mixture of distinct dialogue tasks. We pre-train UFA on a large-scale Chinese customer service corpus collected from practical scenarios and get significant improvements on both natural language understanding (NLU) and natural language generation (NLG) benchmarks.