Dialogue Graph Modeling for Conversational Machine Reading
This work aims to improve the ability of machines to answer complex questions through interactive dialogues, which is an incremental improvement for conversational AI systems.
This paper proposes a dialogue graph modeling framework to enhance machine understanding and reasoning in Conversational Machine Reading (CMR) tasks. The framework utilizes three types of graphs—Discourse Graph, Decoupling Graph, and a global graph—to process rule documents, user scenarios, and dialogue history, ultimately enabling the system to answer questions with "Yes/No/Irrelevant" or ask clarifying questions.
Conversational Machine Reading (CMR) aims at answering questions in a complicated manner. Machine needs to answer questions through interactions with users based on given rule document, user scenario and dialogue history, and ask questions to clarify if necessary. In this paper, we propose a dialogue graph modeling framework to improve the understanding and reasoning ability of machine on CMR task. There are three types of graph in total. Specifically, Discourse Graph is designed to learn explicitly and extract the discourse relation among rule texts as well as the extra knowledge of scenario; Decoupling Graph is used for understanding local and contextualized connection within rule texts. And finally a global graph for fusing the information together and reply to the user with our final decision being either "Yes/No/Irrelevant" or to ask a follow-up question to clarify.