A Hybrid Architecture for Multi-Party Conversational Systems
This work addresses the problem of building conversational systems for multi-party interactions, but it appears incremental as it builds on existing methods without introducing a major breakthrough.
The paper tackles the challenges of designing multi-party conversational systems by proposing a hybrid architecture that combines rules and machine learning, and it reports insights from implementing and evaluating the system in the finance domain.
Multi-party Conversational Systems are systems with natural language interaction between one or more people or systems. From the moment that an utterance is sent to a group, to the moment that it is replied in the group by a member, several activities must be done by the system: utterance understanding, information search, reasoning, among others. In this paper we present the challenges of designing and building multi-party conversational systems, the state of the art, our proposed hybrid architecture using both rules and machine learning and some insights after implementing and evaluating one on the finance domain.