We present a document-grounded matching network (DGMN) for response selection
that can power a knowledge-aware retrieval-based chatbot system. The challenges
of building such a model lie in how to ground conversation contexts with
background documents and how to recognize important information in the
documents for matching. To overcome the challenges, DGMN fuses information in a
document and a context into representations of each other, and dynamically
determines if grounding is necessary and importance of different parts of the
document and the context through hierarchical interaction with a response at
the matching step. Empirical studies on two public data sets indicate that DGMN
can significantly improve upon state-of-the-art methods and at the same time
enjoys good interpretability.

本研究提出了一种基于文档匹配的网络对话模型 (DGMN)，用于支持知识感知的基于检索的聊天机器人系统，在匹配过程中，通过信息融合和层次交互，动态确定文档和上下文的关键信息，实验结果表明，该模型能够显著提高现有方法的表现，并具有良好的可解释性。