CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912689571233792 |
|---|---|
| author | Straka, Milan |
| author_facet | Straka, Milan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17858 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution Straka, Milan Computation and Language 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. |
| title | CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.17858 |