Search Results for author: Andrea Lekkas

Found 1 papers, 0 papers with code

Multi-Sense Language Modelling

no code implementations NAACL (DistCurate) 2022 Andrea Lekkas, Peter Schneider-Kamp, Isabelle Augenstein

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy).

Graph Attention Language Modelling +1

Cannot find the paper you are looking for? You can Submit a new open access paper.