Digital Humanities Forum: Text Analysis for Literary and Historical Texts in Classical Chinese


Tuesday, April 18, 2017, 12:00pm to 1:00pm


Common Room, Harvard-Yenching Library

SPEAKER(S): Chao-Lin Liu 劉昭麟 is a Distinguished Professor in the Department of Computer Science at National Chengchi University (Taiwan). He received a doctoral degree from the Department of Electrical Engineering and Computer Science of the College of Engineering of the University of Michigan. His research interests include natural language processing, cognitive studies, automatic reasoning, and machine learning. He has been actively engaged in digital humanities of East Asian studies and is currently participating in Harvard’s China Biographical Database(CBDB) project.
CONTACT INFO: Feng-en Tu (
With the rapidly increasing availability of digitized texts, researchers can identify and study relevant materials that are extracted from a wide array of sources with the help of search engines. Software tools for text analysis further assist researchers to inspect the texts from several possible viewpoints. We can compare poets’ styles from a distant reading perspective. We can also build social networks among poets and even attempt to compare the imagery in the poems. Techniques of information extractions prove to be instrumental for building the China Biographical Database. Although the tools alone cannot pinpoint useful data yet, they have shown practical usability in reducing the human labor that would be required for extracting biographical information from large corpora like local gazetteers (中國地方志) and tomb biographies (e.g.,《唐代墓誌銘彙編》).

See also: Lecture