CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918529713831936 |
|---|---|
| author | Straka, Milan |
| author_facet | Straka, Milan |
| contents | We introduce CorPipe 26, our winning submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. The fifth edition of this shared task focuses mainly on the comparison of generative LLMs and specialized systems; additionally, 5 more datasets and 2 new languages are introduced. CorPipe 26 is an improved version of CorPipe 25, with a new variant predicting empty nodes together with mentions and coreference links in a single model. Our system outperforms all other submissions in the LLM track by 2.8 percent points and all submissions in the unconstrained track by 9.5 percent points. Furthermore, we perform a series of ablation experiments with different model sizes, empty node prediction methods, and cross-lingual zero-shot evaluation. The source code and the trained models are publicly available at https://github.com/ufal/crac2026-corpipe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30133 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution Straka, Milan Computation and Language We introduce CorPipe 26, our winning submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. The fifth edition of this shared task focuses mainly on the comparison of generative LLMs and specialized systems; additionally, 5 more datasets and 2 new languages are introduced. CorPipe 26 is an improved version of CorPipe 25, with a new variant predicting empty nodes together with mentions and coreference links in a single model. Our system outperforms all other submissions in the LLM track by 2.8 percent points and all submissions in the unconstrained track by 9.5 percent points. Furthermore, we perform a series of ablation experiments with different model sizes, empty node prediction methods, and cross-lingual zero-shot evaluation. The source code and the trained models are publicly available at https://github.com/ufal/crac2026-corpipe. |
| title | CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.30133 |