2 papers
cs.CL2022
Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classification
Jared Mowery
Background: Neural networks produce biased classification results due to correlation bias (they learn correlations between their inputs and outputs to classify samples, even when t…
cs.CL2021
Contrastive Clustering: Toward Unsupervised Bias Reduction for Emotion and Sentiment Classification
Jared Mowery
Background: When neural network emotion and sentiment classifiers are used in public health informatics studies, biases present in the classifiers could produce inadvertently misle…