Contract Statements Knowledge Service for Chatbots
This work addresses the problem of handling contractual questions in chatbots for users needing automated contract assistance, representing an incremental improvement in knowledge engineering for specific domains.
The paper tackles the challenge of formalizing complex contract statements for chatbots by identifying key statements and modeling their rules with a novel knowledge engineering method, resulting in a user-friendly tool that enables scalable integration into chatbot frameworks.
Towards conversational agents that are capable of handling more complex questions on contractual conditions, formalizing contract statements in a machine readable way is crucial. However, constructing a formal model which captures the full scope of a contract proves difficult due to the overall complexity its set of rules represent. Instead, this paper presents a top-down approach to the problem. After identifying the most relevant contract statements, we model their underlying rules in a novel knowledge engineering method. A user-friendly tool we developed for this purpose allows to do so easily and at scale. Then, we expose the statements as service so they can get smoothly integrated in any chatbot framework.