Counterfactual inference for text classification debiasing

C Qian, F Feng, L Wen, C Ma, P **e - Proceedings of the 59th …, 2021‏ - aclanthology.org
Today's text classifiers inevitably suffer from unintended dataset biases, especially the
document-level label bias and word-level keyword bias, which may hurt models' …

Dale: Generative data augmentation for low-resource legal nlp

S Ghosh, CK Evuru, S Kumar… - arxiv preprint arxiv …, 2023‏ - arxiv.org
We present DALE, a novel and effective generative Data Augmentation framework for low-
resource LEgal NLP. DALE addresses the challenges existing frameworks pose in …

Enhancing text classification via discovering additional semantic clues from logograms

C Qian, F Feng, L Wen, L Lin, TS Chua - Proceedings of the 43rd …, 2020‏ - dl.acm.org
Text classification in low-resource languages (eg Thai) is of great practical value for some
information retrieval applications (eg sentiment-analysis-based restaurant …