Video Recordings

Coreference resolution research has long been dominated by English-centric evaluation, partly due to the heterogeneity of available resources. To address this imbalance, my colleagues and I have been developing CorefUD, a growing multilingual collection of datasets annotated with coreference and anaphoric relations. We also organize the CRAC Shared Tasks, aiming to promote cross-linguistic research in this area.

In this talk, I will share our progress over the past four years, the challenges we have faced, and discuss to what extent our efforts have driven meaningful change in the field.