The PERKS project supports the holistic governance of industrial PK in its entire life cycle, from elicitation to management and from access to exploitation. PERKS bases its solutions on leading-edge AI (both symbolic and subsymbolic) and data technologies, by advancing and integrating existing methodologies and tools in terms of readiness, flexibility and user acceptance. Besides AI and data, the third pillar of PERKS consists of people: the goal is to put industry workers at the centre, in line with the Industry 5.0 vision, to satisfy their concrete needs, to provide AI-powered digital tools to perform their tasks better and more easily, following a human-in-the-loop paradigm to enhance the technologies and the solutions.
In the scope of PERKS, the team at the MLT lab will look into the computational modeling and elicitation of procedural knowledge. We will leverage newest AI technology, including transfer-learning deep networks for information retrieval and generative language models, to learn computational representations of procedural knowledge from textual sources. We will investigate multimodal extensions of our work, also taking into account graphs and figures from texts, and various text types for pre-training and finetuning our models. Moreover, we will contribute towards automatically generating questions as FAQs from technical documents.
Partners
Cefriel, Fagor Automation, IDC, NTT DATA, Onlim, Siemens, Whirlpool, Wirtschaftsuniversität Wien
