Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification
Recent advances in weakly supervised text classification mostly focus on designing sophisticated methods to turn high-level human heuristics into quality pseudo-labels. In this paper, we revisit the seed matching-based method, which is arguably the simplest way to generate pseudo-labels, and show that its power was greatly underestimated. We show that the limited performance of seed matching is largely due to the label bias injected by the simple seed-match rule, which prevents the classifier from learning reliable confidence for selecting high-quality pseudo-labels. Interestingly, simply deleting the seed words present in the matched input texts can mitigate the label bias and help learn better confidence. Subsequently, the performance achieved by seed matching can be improved significantly, making it on par with or even better than the state-of-the-art. Furthermore, to handle the case when the seed words are not made known, we propose to simply delete the word tokens in the input text randomly with a high deletion ratio. Remarkably, seed matching equipped with this random deletion method can often achieve even better performance than that with seed deletion.
Code (1)
Tasks
text-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting the Importance of Amplifying Bias for Debiasing
In image classification, "debiasing" aims to train a classifier to be less susceptible to dataset bias, the strong correlation between peripheral attributes of data samples and a target class. For example, even if the fr…
Attributeimage-classificationImage ClassificationAdaptive Markov State Model estimation using short reseeding trajectories
In the last decade, advances in molecular dynamics (MD) and Markov State Model (MSM) methodologies have made possible accurate and efficient estimation of kinetic rates and reactive pathways for complex biomolecular dyna…
Protein FoldingLearning Bias-reduced Word Embeddings Using Dictionary Definitions
Pre-trained word embeddings, such as GloVe, have shown undesirable gender, racial, and religious biases. To address this problem, we propose DD-GloVe, a train-time debiasing algorithm to learn word embeddings by leveragi…
Word EmbeddingsDiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection
Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous e…
Synthetic Data GenerationCompressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)