Vasileios Lioutas, Ahmad Rashid, Mehdi Rezagholizadeh
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standard benchmarks has scaled with size, compression techniques such as knowledge distillation have been key in making them practical. We present MATE-KD, a novel textbased adversarial training algorithm which improves the performance of knowledge distillation. MATE-KD first trains a masked language model-based generator to perturb text by maximizing the divergence between teacher and student logits. Then using knowledge distillation a student is trained on both the original and the perturbed training samples. We evaluate our algorithm, using BERT-based models, on the GLUE benchmark and demonstrate that MATE-KD outperforms competitive adversarial learning and data augmentation baselines. On the GLUE test set our 6 layer RoBERTa based model outperforms BERT LARGE .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.05912")
get_code_for_paper("2105.05912")
have("2105.05912")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2105.05912.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2105.05912)
Connect an agent — have() is free.