Lectures in course HUM-369: Digital humanities

Introduces students to digital humanities through practical exercises, such as working on a large ongoing project.

Impresso: Newspaper Archives Exploration

Explores historical newspaper archives through OCR quality, named entities, topic modeling, and text reuse analysis.

Explores the analysis of large numbers in linguistics and the evolution of language complexity using various texts and corpora.

Document Segmentation: dhSegment

Explores the development and improvements of dhSegment, an open-source document segmentation package using PyTorch.

Concept-Based Image Systems

Explores concept-based, named entity-based, and perspective connections-based image systems, emphasizing the analysis of graphics and visual relationships between images.

Named Entities Analysis

Covers various projects related to bots developed by students at EPFL.

Bots: Wikipedia Wikification

Delves into the role of bots in Wikipedia, their wikification of public domain content, and the controversies surrounding their use.