BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval
BELXTR is presented, a novel embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage token-level matching information in biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion.
Samuele Garda, U. Leser
· 0 citations