Presenter: Alkis KoudounasMonday, March 11th, 2024 5:00 PMLocation: Sala Piccola Covivio, Corso Ferrucci 112 ABSTRACT Enhancing end-to-end spoken language understanding (E2E SLU) models performance, particularly for voice assistants, poses challenges in interpretability and transparency. Our research, in collaboration with Amazon Alexa AI, investigates the performance of E2E SLU models. We utilize […]
NIKHIL JHA
30 posts
Presenter: Giovanni LivragaMonday, February 26th, 2024 5:30 PMLocation: Sala Grande Covivio, Corso Ferrucci 112 ABSTRACT Supporting data owners in maintaining full control over their data is a key requirement in scenarios characterized by outsourcing and/or sharing. Not only does it facilitate compliance with regulations and ethical standards – it can […]
Presenter: Alessandro RussoMonday, February 12th, 2024 5:30 PMLocation: Sala Piccola Covivio, Corso Ferrucci 112 ABSTRACT In recent years, Neuro-Symbolic AI (NeSy) techniques, particularly within the Logic Tensor Networks (LTN) framework, have driven significant advancements in Computer Vision by integrating symbolic reasoning within neural networks. This hybrid paradigm holds promise for […]
Presenter: Pierrick LeroyMonday, January 29th, 2024 5:30 PMLocation: Sala Grande Covivio, Corso Ferrucci 112 ABSTRACT A trained (deep) learning model is a sequence of maps and spaces. Data, old and new, are mapped through the model strata from input to output. The main ingredients are a training set of samples […]
Presenter: Enrico PalumboMonday, January 15th, 2024 5:30 PMLocation: Sala Piccola Covivio, Corso Ferrucci 112 ABSTRACT Allowing users to discover new entities such as books, music, and movies is an important goal for online platforms. Exploratory queries such as “new indie rock releases” or “acoustic guitar covers to learn” can help […]
Presenter: Lorenzo VaianiMonday, November 27th, 2023 17:30Location: SmartData@Covivio, Sala Grande With the proliferation of multimodal data sources, detecting fake news content has become more and more challenging as fake content can be hidden in either visual or textual news elements. Our work addresses the automatic detection of Italian fake news […]