From October 67th, 2022, Lab member Fabio participated in the 10th annual “New Directions in Analyzing Text as Data” conference (TADA), which is a leading forum for research on the study of politics, society, and culture through computational analysis of documents. At this year’s conference, Fabio presented a talk titled “Where Did It Come From? Deep Learning for Event Extraction in Art Provenance”.
In the talk, he explored the possibilities offered by artificial intelligence in the structuring of provenance events, where events are composed of parties, locations, dates, and methods of transfer. In particular, Fabio focused on the possibilities of applying deep learning methods, i.e. tools using artificial intelligence, for event extraction from provenance. From a computer science perspective, the extraction of knowledge from a provenance text relates to an event extraction problem in Natural Language Processing (NLP), an area of research where computer science, linguistics, and, more recently, artificial intelligence intersect. Using a museum dataset of over 11,000 provenances, Fabio showed how it is possible to solve NLP tasks by training artificial intelligence.