.png){kind=icon}
返回
Improving Semi-Supervised Text Classification with Dual Meta-Learning
.png){kind=icon}
OA
AI
DOI：10.1145/3648612.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The goal of semi-supervised text classification (SSTC) is to train a model by exploring both a small number of labeled data and a large number of unlabeled data, such that the learned semi-supervised classifier performs better than the supervised classifier trained on solely the labeled samples. Pseudo-labeling is one of the most widely used SSTC techniques, which trains a teacher classifier with a small number of labeled examples to predict pseudo labels for the unlabeled data. The generated pseudo-labeled examples are then utilized to train a student classifier, such that the learned student classifier can outperform the teacher classifier. Nevertheless, the predicted pseudo labels may be inaccurate, making the performance of the student classifier degraded. The student classifier may perform even worse than the teacher classifier. To alleviate this issue, in this paper, we introduce a dual meta-learning (DML) technique for semi-supervised text classification, which improves the teacher and student classifiers simultaneously in an iterative manner. Specifically, we propose a meta-noise correction method to improve the student classifier by proposing a Noise Transition Matrix (NTM) with meta-learning to rectify the noisy pseudo labels. In addition, we devise a meta pseudo supervision method to improve the teacher classifier. Concretely, we exploit the feedback performance from the student classifier to further guide the teacher classifier to produce more accurate pseudo labels for the unlabeled data. In this way, both teacher and student classifiers can co-evolve in the iterative training process. Extensive experiments on four benchmark datasets highlight the effectiveness of our DML method against existing state-of-theart methods for semi-supervised text classification. We release our code and data of this paper publicly at https://github.com/GRIT621/DML.
Keyword:
Semi-supervised text classification
pseudo labeling
noise transition matrix
meta learning
consistency regularization
期刊
IF:
9.1
论文数:
1.2K
被引数:
4.7K
机构
引用论文
.png){kind=icon}
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation通过不确定性估计纠正伪标签学习，用于领域自适应语义分割
PREAI
分享收藏
SEX DISPARITIES IN IN-HOSPITAL TREATMENTS, OUTCOMES, AND RESOURCE UTILIZATION AMONG PERITONEAL DIALYSIS PATIENTS: A NATIONWIDE INPATIENT SAMPLE ANALYSIS住院治疗、结局和资源利用中的性别差异：一项全国住院样本分析（在腹膜透析患者中）
PREAI
分享收藏分享收藏
查看更多内容