A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912469923921920 |
|---|---|
| author | Costa, Nelson Filipe Kosseim, Leila |
| author_facet | Costa, Nelson Filipe Kosseim, Leila |
| contents | We propose a novel multi-label classification approach to implicit discourse relation recognition (IDRR). Our approach features a multi-task model that jointly learns multi-label representations of implicit discourse relations across all three sense levels in the PDTB 3.0 framework. The model can also be adapted to the traditional single-label IDRR setting by selecting the sense with the highest probability in the multi-label representation. We conduct extensive experiments to identify optimal model configurations and loss functions in both settings. Our approach establishes the first benchmark for multi-label IDRR and achieves SOTA results on single-label IDRR using DiscoGeM. Finally, we evaluate our model on the PDTB 3.0 corpus in the single-label setting, presenting the first analysis of transfer learning between the DiscoGeM and PDTB 3.0 corpora for IDRR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08971 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition Costa, Nelson Filipe Kosseim, Leila Computation and Language We propose a novel multi-label classification approach to implicit discourse relation recognition (IDRR). Our approach features a multi-task model that jointly learns multi-label representations of implicit discourse relations across all three sense levels in the PDTB 3.0 framework. The model can also be adapted to the traditional single-label IDRR setting by selecting the sense with the highest probability in the multi-label representation. We conduct extensive experiments to identify optimal model configurations and loss functions in both settings. Our approach establishes the first benchmark for multi-label IDRR and achieves SOTA results on single-label IDRR using DiscoGeM. Finally, we evaluate our model on the PDTB 3.0 corpus in the single-label setting, presenting the first analysis of transfer learning between the DiscoGeM and PDTB 3.0 corpora for IDRR. |
| title | A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.08971 |