UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations
This work describes a self-supervised data augmentation approach used to improve learning models’ performances when only a moderate amount of labeled data is available. Multiple copies of the original model are initially trained on the downstream task. Their predictions are then used to annotate a l...
Gardado en:
| Autor Principal: | |
|---|---|
| Formato: | Chapter |
| Idioma: | Inglês |
| Publicado: |
Accademia University Press
2020
|
| Acceso en liña: | https://doi.org/10.4000/books.aaccademia.7733 https://hdl.handle.net/20.500.13089/1djq https://books.openedition.org/aaccademia/7733 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|