2022
Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals
EMNLP 2022main
For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models aiming to avoid this spurious pattern problem, adding extra coun…