Papers by Mustafa Sir
Leveraging Task Transferability to Meta-learning for Clinical Section Classification with Limited Data (2022.acl-long)
Copied to clipboard
| Challenge: | Existing text classification systems require thousands of in-domain text data to achieve high performance. |
| Approach: | They propose an algorithm to improve task transferability of meta-learning-based text classification by normalizing negative conditional entropy from source task data to boost cross-domain meta- learning accuracy. |
| Outcome: | The proposed method improves section classification accuracy significantly compared to meta-learning algorithms. |