论文标题
对话机器阅读的对话图建模
Dialogue Graph Modeling for Conversational Machine Reading
论文作者
论文摘要
对话机读取（CMR）旨在以复杂的方式回答问题。机器需要根据给定规则文档，用户场景和对话历史记录与用户的互动来回答问题，并提出问题以澄清必要。在本文中，我们提出了一个对话图建模框架，以提高机器在CMR任务上的理解和推理能力。总共有三种类型的图。具体而言，话语图旨在明确学习并提取规则文本之间的话语关系以及对场景的额外知识。去耦图用于理解规则文本中的本地和上下文化连接。最后，将信息融合在一起的全局图，并以我们的最终决定为“是/否/无关紧要”，或者提出后续问题以澄清。
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.
