AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service
This work addresses the problem of handling complicated business knowledge and real-world questions in e-commerce customer service, representing an incremental application of KBQA technology in a specific industry domain.
The paper tackles the challenge of applying knowledge base question answering (KBQA) to complex e-commerce customer service by extending the SPO structure with property hierarchy, key-value structure, and compound value type, and enhancing it with constraints recognition and reasoning. It reports successful deployment during the 'Double 11' period in 2018, improving resolution, customer satisfaction, and knowledge management efficiency.
With the rise of knowledge graph (KG), question answering over knowledge base (KBQA) has attracted increasing attention in recent years. Despite much research has been conducted on this topic, it is still challenging to apply KBQA technology in industry because business knowledge and real-world questions can be rather complicated. In this paper, we present AliMe-KBQA, a bold attempt to apply KBQA in the E-commerce customer service field. To handle real knowledge and questions, we extend the classic "subject-predicate-object (SPO)" structure with property hierarchy, key-value structure and compound value type (CVT), and enhance traditional KBQA with constraints recognition and reasoning ability. We launch AliMe-KBQA in the Marketing Promotion scenario for merchants during the "Double 11" period in 2018 and other such promotional events afterwards. Online results suggest that AliMe-KBQA is not only able to gain better resolution and improve customer satisfaction, but also becomes the preferred knowledge management method by business knowledge staffs since it offers a more convenient and efficient management experience.