CLSep 22, 2025

CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution

arXiv:2509.17858v21 citationsh-index: 2Has CodeProceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference
Originality Synthesis-oriented
AI Analysis

This work addresses coreference resolution for multilingual NLP applications, but it is incremental as it builds on previous shared task entries with a reimplementation.

The authors tackled multilingual coreference resolution by presenting CorPipe 25, which won the CRAC 2025 Shared Task by outperforming all other submissions by 8 percentage points in both LLM and unconstrained tracks.

We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points. The source code and trained models are publicly available at https://github.com/ufal/crac2025-corpipe.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes