Historical Text

Research on historical text focuses on developing computational methods to analyze large-scale digitized archives, addressing challenges like archaic language, OCR errors, and the lack of standardized annotations. Current efforts utilize various machine learning techniques, including large language models (LLMs), transformer architectures, and topic modeling, to extract information, identify patterns, and disambiguate entities within these texts. This work is significant for advancing digital humanities research, enabling large-scale analysis of historical events, social dynamics, and cultural evolution that would be impossible through manual methods alone.

Papers