Hi there 👋 !
Impresso - Media Monitoring of the Past is an interdisciplinary research project that uses machine learning to pursue a paradigm shift in the processing, semantic enrichment, representation, exploration and study of historical media across modalities, temporal, linguistic, and national borders. The project has received two rounds of funding, from 2017-2020 and 2023-2027 (hence, there is code from both periods).
We design and develop the Impresso Web App and the upcoming Impresso Datalab (coming soon), while conducting research at the intersection of Natural Language Processing, Design, and History. Find more details on the project website.
This GitHub organization hosts numerous repositories dedicated to:
- the code behind the Web App and Datalab. While a few repositories are public, many are still private. We aim to document and release code properly as it matures and becomes ready;
- code supporting research efforts;
- code from student projects.
More information and highlights will be shared as we continue to make progress! In addition to the public repositories listed below, you can also check out our models on the Impresso Hugging Face organisation.
(to come)
