Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of...
Enregistré dans:
| Dans: | URI:https://journals.openedition.org/ijcol, |
|---|---|
| Auteurs principaux: | , , , |
| Format: | Article ou chapitre numérique |
| Langue: | Anglais |
| Publié: |
IJCoL
2020
|
| Accès en ligne: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |