This talk offers a practice-oriented overview of my published Digital Humanities research on classical Chinese texts. Drawing on a series of studies using domain-specific pre-trained language models, I reflect on practical experiences with word segmentation, part-of-speech tagging, named entity recognition, keyword extraction, and stylistic analysis. Rather than focusing on technical performance alone, the lecture highlights methodological decisions, annotation strategies, and interpretive challenges that arise when applying NLP methods to historical, non-segmented languages. I will present these works as a cumulative research trajectory and conclude with an open discussion on methodological transferability and human-in-the-loop approaches in Digital Humanities.

This is a hybrid event; the details will be shared upon registration.

Speaker:

Yiqin Zhang is a PhD candidate in Information Management at Nanjing University and a visiting researcher in Digital Humanities at King’s College London. Her research focuses on applying NLP and pre-trained language models to historical Chinese texts, with an emphasis on methodological reflection and practical DH workflows. She has published multiple studies in Chinese DH and information science journals on text annotation and semantic analysis of classical Chinese corpora.