Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
This addresses the challenge of handling multi-turn dialogues in customer service, though it appears incremental as it builds on existing retrieval-augmented methods.
The authors tackled the problem of multi-turn customer service chatbots by introducing Lingke, which uses information retrieval and fine-grained processing to generate responses from product documents, achieving improved performance in multi-turn conversations.
Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.