Findings of the Third Shared Task on Multilingual Coreference Resolution

TL;DR

This paper reports on the third multilingual coreference resolution shared task, emphasizing increased complexity with zero anaphora, diverse languages including historical ones, and the participation of six systems.

Contribution

It introduces a more realistic and diverse multilingual coreference resolution challenge, expanding previous tasks with zero anaphora and historical languages, and provides an overview of participating systems.

Findings

Six systems participated in the shared task.

Increased difficulty due to zero anaphora without gold slots.

Expanded language coverage including historical languages.

Abstract

The paper presents an overview of the third edition of the shared task on multilingual coreference resolution, held as part of the CRAC 2024 workshop. Similarly to the previous two editions, the participants were challenged to develop systems capable of identifying mentions and clustering them based on identity coreference. This year's edition took another step towards real-world application by not providing participants with gold slots for zero anaphora, increasing the task's complexity and realism. In addition, the shared task was expanded to include a more diverse set of languages, with a particular focus on historical languages. The training and evaluation data were drawn from version 1.2 of the multilingual collection of harmonized coreference resources CorefUD, encompassing 21 datasets across 15 languages. 6 systems competed in this shared task.