Document AI, or Document Intelligence, refers to techniques for automatically reading, understanding, and analyzing documents. In this project, we analyze different thypes of document corpus to uncover their implicit structure and relationships. Based on the structured analysis, we develop novel systems for various applications.
We developed the Story Forest system to automatically cluster news documents into events, while connecting related events in a growing tree structure to tell an evolving story. Story Forest has been deployed into Tencent QQ Browser for document clustering and hot event discovery.
We introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query. To serve as a research benchmark, we further propose SurveyBank, a dataset consisting of large quantities of survey papers in the field of computer science as well as their citation relationships. A real-time Reading Path Generation (RePaGer) system has been also implemented with our designed model.