Search Results for author:
Found 2 papers, 0 papers with code
Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality
To alleviate these challenges, we propose a character-based subword module (char2subword) that learns the subword embedding table in pre-trained models like BERT.
Improving out-of-distribution generalization via multi-task self-supervised pretraining
Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness.
Ranked #116 on
Domain Generalization
on PACS
Cannot find the paper you are looking for? You can
Submit a new open access paper.
