ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution
This work addresses coreference resolution for multiple languages, showing broad effectiveness but is incremental as it builds on existing models and methods.
The paper tackled multilingual coreference resolution by fine-tuning a large multilingual Transformer model, achieving winning performance in the CRAC 2022 shared task with improvements across all datasets, not just underrepresented languages.
We describe the winning submission to the CRAC 2022 Shared Task on Multilingual Coreference Resolution. Our system first solves mention detection and then coreference linking on the retrieved spans with an antecedent-maximization approach, and both tasks are fine-tuned jointly with shared Transformer weights. We report results of fine-tuning a wide range of pretrained models. The center of this contribution are fine-tuned multilingual models. We found one large multilingual model with sufficiently large encoder to increase performance on all datasets across the board, with the benefit not limited only to the underrepresented languages or groups of typologically relative languages. The source code is available at https://github.com/ufal/crac2022-corpipe.