Machine learning provides new ways to process large amounts of unstructured documents. As information managers, archivists and librarians, how can we understand in a better way possibilities and limits of this new approach? ULB organises this free one day workshop, allowing researchers and practitioners to come together and share experiences.
The morning session will allow each participant to experiment hands-on with Topic Modeling and Word Embeddings, but also with data cleaning tools. International experts and academics will share their research in the afternoon session. Among them is Mette van Essen from the Dutch National Archives, a partner in the Digital Heritage Network, presenting the results of a case study to classify email with supervised machine learning. Throughout the day, discussion and exchange of ideas is paramount and will be promoted in various ways.
Read more about the programme and registration on the website.