Papers by Mohand Boughanem
Rebalancing Label Distribution While Eliminating Inherent Waiting Time in Multi Label Active Learning Applied to Transformers (2024.lrec-main)
Copied to clipboard
| Challenge: | Data annotation is a resourceintensive endeavor, necessitating human involvement and expertise. |
| Approach: | They propose to annotate instances to rebalance label distribution by judiciously selecting and limiting the data to be annotated. |
| Outcome: | The proposed method mitigates biases, improves model performance and reduces strategy-dependent disparities. |
Explanation Extraction from Hierarchical Classification Frameworks for Long Legal Documents (2024.findings-naacl)
Copied to clipboard
| Challenge: | Hierarchical classification frameworks are black boxes with no explanation for their predictions. |
| Approach: | They develop an extractive explanation algorithm for hierarchical frameworks for long sequences based on the sensitivity of the trained model to input perturbations. |
| Outcome: | The proposed algorithm achieves a minimum gain of 1 point over the previous benchmark on most of the performance metrics. |