← Search

Seung Jun Moon

1 accepted papers

2021

MASKER: Masked Keyword Regularization for Reliable Text Classification

AAAI 2021technical

Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned text classifiers is an often underlooked performance criterion…