Name
Title | ||
|---|---|---|
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation. |
Abstract | ||
|---|---|---|
Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer Distillation, Data Augmentation, and Adversarial Training. In this work, we propose a learning-based data augmentation technique tailored for knowledge distillation, called CILDA. To the best of our knowledge, this is the first time that intermediate layer representations of the main task are used in improving the quality of augmented samples. More precisely, we introduce an augmentation technique for KD based on intermediate layer matching using contrastive loss to improve masked adversarial data augmentation. CILDA outperforms existing state-of-the-art KD approaches on the GLUE benchmark, as well as in an out-of-domain evaluation. |
Year | Venue | DocType |
|---|---|---|
2022 | International Conference on Computational Linguistics | Conference |
Volume | Citations | PageRank |
Proceedings of the 29th International Conference on Computational Linguistics | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Md Akmal Haidar | 1 | 0 | 0.68 |
| Mehdi Rezagholizadeh | 2 | 3 | 8.82 |
| Abbas Ghaddar | 3 | 0 | 0.68 |
| Khalil Bibi | 4 | 0 | 1.01 |
| Phillippe Langlais | 5 | 0 | 0.68 |
| Pascal Poupart | 6 | 4 | 2.79 |