Hello everyone! I tried to apply the technique of data augmentation, mixup, popularly used on computer vision, but in this case on NLP. The algorithm developed is in two phases: The first phase gets the representation for each sentence of the batch, computing the mean of the correspondent hidden …

Using mixup on RoBERTa

replydotai July 15, 2020, 9:16pm 4

Thanks for sharing @sgugger.
Data augmentation for text classification really is a tough one. Is there anything you consider promising?

@franborjavalero you might want to checkout this thread

1 Like

Topic		Replies	Views
Replication of the performance of RoBERTa on the COPA task Models	0	449	December 19, 2022
Overlapping data between pre-training and fine-tuning stages 🤗Transformers	0	216	October 8, 2021
Fundamental newbie questions Beginners	1	1067	December 6, 2020
Incremental training on unlabeled data using MLM 🤗Transformers	0	528	December 10, 2022
Multi-Output Regression using Pre-trained LLM (Roberta) 🤗Transformers	1	664	September 18, 2023