UNIFR Talk - Recent achievements in large-scale multilingual text understanding

Speaker: Prof. Roberto Navigli, La Sapienza University, Rome

In this talk I will present work done in my group at the Computer Science Department of the Sapienza University of Rome which addresses key problems in multilingual lexical semantics. Starting from a brief introduction to BabelNet, the largest multilingual semantic network and encyclopedic dictionary covering 14 million concepts and entities, and 271 languages, I will move on to Word Sense Disambiguation and Entity Linking in arbitrary languages with "zero training" (Babelfy) and latent (SensEmbed) and explicit (NASARI) vector representations of meaning (the latter of which based on neural networks embeddings of meanings) which obtain state-of-the-art results in several NLP tasks. This is joint work with several people from my NLP group at Sapienza.

1 person is attending this meetup

Open in Google Maps