What We Do

Publications

Advancing Extreme Multi-Label Text Classification for Less-Represented Languages

Dr Nada Lavrač has published a new research article titled “Extreme Multi-Label Text Classification for Less-Represented Languages and Low-Resource Environments: Advances and Lessons Learned” with co-authors. The study addresses a major challenge in contemporary Natural Language Processing...

AR-Q-former: Historical Newspaper Article Separation Based on Multilingual Transformer Structure

A novel multimodal approach for article separation in historical newspapers leverages both textual data and visual information to improve segmentation accuracy.

AI methods for studying media homogenisation

This article briefly explains one case study where media and journalism scholars productively come together with computer science scholars.

Open Science More publications

Study

Masters’ curriculum

The AI4DH team will build a curriculum for the “Artificial Intelligence for Digital Humanities” Master module. The curriculum will not only provide a comprehensive education in AI but also cultivate an understanding of its applications and implications in the humanities, preparing students for interdisciplinary research or careers at the nexus of technology and humanistic studies. The curriculum will define expected learning outcomes, curriculum structure, course content and delivery, and assessment methods. It will plan necessary support and resources, students’ feedback, and iterative revisions. It will propose extracurricular activities, such as career guidance.

PhD level courses

The project will build at least two courses at PhD level to be included into UL PhD programmes, such as Computer Science, Digital Linguistics, Humanities and Social Sciences. The courses will be designed to provide PhD students with a comprehensive and in-depth understanding of how AI technologies can be applied to various fields within the DH, emphasizing both technical mastery and critical analysis. The contents shall cover relevant topics such as advanced computational methods in DH research, ethics and AI with critical perspectives in DH, machine learning for digital cultural heritage, natural language processing in historical and literary analysis, AI-driven approaches to social and cultural analytics, AI for linguistics and others.

Micro-credentials curricula

Micro-credentials certify the learning outcomes of short-term learning experiences, for example, a short course or training. They offer a flexible, targeted way to help people develop the knowledge, skills, and competences they need for their personal and professional development.

Offering micro-credentials in the area of AI for DH can provide professionals, graduates, and researchers with focused expertise and skills that are highly relevant and applicable in today’s interdisciplinary academic and industry landscapes. Micro-credentials allow individuals to upskill or reskill in targeted aspects of AI applications within DH. Several possible micro-credentials could be offered, such as AI ethics and society, Digital humanities tools and techniques, large language models for DH, AI in cultural heritage, Machine learning for data-driven historical research, AI and linguistics, Bias detection and mitigation in AI Systems, etc. We will create 5 micro-credentials and make them available online, through the DariahTeach platform.