New Frontiers in AI Paper

06 October 2022

I’m pleased to finally have this paper Affordance Embeddings for Situated Language Understanding published in the Language and Computation section of the Frontiers in AI journal, as part of the special issue Perspectives for Natural Language Processing between AI, Linguistics and Cognitive Science. We use vectorizations of VoxML affordance encodings to perform transfer learning to reason about the properties of unknown objects in a zero-shot condition. We’ve been trying to get this work published for a couple of years now, so it’s a very good feeling to finally have it out in a major journal. The paper is open access and can be read here.