ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916440980848640 |
|---|---|
| author | Straka, Milan Straková, Jana |
| author_facet | Straka, Milan Straková, Jana |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_07278 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution Straka, Milan Straková, Jana Computation and Language 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. |
| title | ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2209.07278 |