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...
Uloženo v:
| Hlavní autoři: | , , , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
Accademia University Press
2017-12-01
|
| Edice: | IJCoL |
| On-line přístup: | https://journals.openedition.org/ijcol/553 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|