Artificial intelligence technology has rapidly changed the study form of humanities. In this presentation, we will discuss the key issues in using natural language processing, deep learning, GIS, database and visualization technologies to design a new digital humanities database from the electronic texts of ancient books. We will introduce automatic tagging tools for ancient Chinese sentence/word segmentation, named entity tagging. Then, we will present a case study of constructing the DH database of Chinese classics Zuozhuan(左傳), Shiji(史記) and Shijing(詩經), which offers word based multi-functional retrieval in addition to the full-text retrieval. Data analysis and visualization also reveal new facts from the texts, such as the personal social relations and travelling distance. Finally, we discuss the potential improvements and applications of the DH database.

Speaker: Bin Li, Visiting Scholar of CBDB group at IQSS, Harvard University. Associate Professor of Applied Linguistics in the School of Chinese Language and Literature, Nanjing Normal University