paper-with-me

홈 › Papers

Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification

2023-05-24 · chengyu dong, Zihan Wang, Jingbo Shang

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.

📄 PDF Abstract BibTeX arXiv:2305.14794

Code (1)

shwinshaker/simseed 공식 구현 pytorch

Tasks

text-classificationText Classification

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Revisiting the Importance of Amplifying Bias for Debiasing

2022-05-29 · Jungsoo Lee, Jeonghoon Park, Daeyoung Kim, Juyoung Lee 외

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 Classification

Adaptive Markov State Model estimation using short reseeding trajectories

2019-12-12

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 Folding

Learning Bias-reduced Word Embeddings Using Dictionary Definitions

2022-05-01 · Findings (ACL) 2022 5 · Haozhe An, Xiaojiang Liu, Donald Zhang

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 Embeddings

DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection

2024-06-10 · Donggeun Ko, Sangwoo Jo, Dongjun Lee, Namjun Park 외

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 Generation

Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering

2022-10-26 · Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu 외

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)