Enhancing Arabic-text feature extraction utilizing label-semantic augmentation in few/zero-shot learning
A growing amount of research use pre-trained language models to address few/zero-shot text classification problems. Most of these studies neglect the semantic information hidden implicitly beneath the natural language names of class labels and develop a meta learner from the input texts solely. In t...
Saved in:
| Main Authors: | , , , |
|---|---|
| 其他作者: | |
| 格式: | Article |
| 語言: | English |
| 出版: |
2023
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/172293 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|