Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
“Hop on the train!” is a semester project from the Digital Humanities master, conceived to explore the interviews archive of the Montreux Jazz Memories project in an interactive fashion, by interconnecting all the different interviews to synthesise new stories. An AI pipeline leverages Large Language Model to process over 400 transcriptions - to clean the texts and classify them into 6 different themes - and then synthesises 6 original stories (one per topic) to unveil new points of view from the people who experienced the festival. The prototype is deployed as an interactive exhibition which is based on a set of train journeys: each train line is a story, and each wagon represents an interviewee and their information. In this way, the full train ride tells a story that is data driven and that has never been read before. In this report, you’ll see the experiments that lead to the final AI pipeline to process the texts and all the inspiration and concepts that lead to the final design.