paper-with-me

Papers

LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Iterative self-training is a popular framework in weakly supervised text classification that involves bootstrapping a deep neural classifier from heuristic pseudo-labels. The quality of pseudo-labels, especially the initial ones, is crucial to final performance but they are inevitably noisy due to their heuristic nature, so selecting the correct ones has a huge potential for performance boost. One straightforward solution is to select samples based on the softmax probability scores corresponding to their pseudo-labels. However, we show through our experiments that such methods are ineffective and unstable due to the erroneously high-confidence predictions from poorly calibrated models. Recent studies on the memorization effects of deep neural models suggest that these models first memorize training samples with clean labels and then those with noisy labels. Inspired by this observation, we propose a novel pseudo-label selection method LOPS that takes learning order of samples into consideration. We hypothesize that the learning order reflects the probability of wrong annotation in terms of ranking, and therefore, select the top samples that are learnt earlier. LOPS can be viewed as a strong performance-boost plug-in to most of existing weakly-supervised text classification methods, as confirmed in extensive experiments on six real-world datasets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationPseudo Labeltext-classificationText Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification

2022-05-25 · Dheeraj Mekala, chengyu dong, Jingbo Shang

Weakly supervised text classification methods typically train a deep neural classifier based on pseudo-labels. The quality of pseudo-labels is crucial to final performance but they are inevitably noisy due to their heuri…

MemorizationPseudo Labeltext-classificationText Classification

Neighborhood-Regularized Self-Training for Learning with Few Labels

2023-01-10 · ran Xu, Yue Yu, Hejie Cui, Xuan Kan 외

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised lear…

Efficient Teacher: Semi-Supervised Object Detection for YOLOv5

2023-02-15 · Bowen Xu, Mingtao Chen, Wenlong Guan, Lulu Hu

Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quali…

Objectobject-detectionObject DetectionPseudo Label+1

Large Language Model-guided Document Selection

2024-06-07 · Xiang Kong, Tom Gunter, Ruoming Pang

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. In…

In-Context LearningLanguage ModelingLanguage ModellingLarge Language Model+1

Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling

2021-08-15 · Hongyi Xu, Fengqi Liu, Qianyu Zhou, Jinkun Hao 외

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes…

3D Object DetectionObjectobject-detectionObject Detection