BabelNet, NounAtlas, Concept-pedia, and Other Marvels: Exploring Semantics in the Age of LLMs

Large Language Models (LLMs) have redefined the distributional paradigm in semantics, demonstrating that large-scale statistical learning can yield emergent representations of meaning. Yet, while these models exhibit impressive linguistic fluency and versatility, their internal representations of meaning remain largely opaque, data-driven, and detached from explicit conceptual structure. This talk revisits the problem of meaning representation from a complementary, knowledge-based perspective, presenting an integrated view of several large-scale semantic resources - including BabelNet, NounAtlas, and Concept-pedia - that aim to provide interpretable, multilingual, and multimodal conceptually-grounded frameworks for modeling lexical and conceptual knowledge.

We will also discuss the potential of explicit semantics to interface with LLMs for enhanced interpretability and semantic alignment. In doing so, the talk argues for a renewed synthesis between symbolic and subsymbolic approaches to meaning, illustrating how curated, multilingual knowledge graphs and data-driven models can jointly contribute to a more comprehensive and transparent account of semantics in the era of large-scale neural language modeling.