SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

arXiv (Cornell University)(2022)

引用 1|浏览20
暂无评分
摘要
Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text classification. SAT first generates two augmented views for each unlabeled data and then trains a meta-learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views. The weakly-augmented view is fed to the model to produce a pseudo-label and the strongly-augmented view is used to train the model to predict the same pseudo-label. We conducted extensive experiments and analyses on three text classification datasets and found that with varying sizes of labeled training data, SAT consistently shows competitive performance compared to existing semi-supervised learning methods. Our code can be found at \url{https://github.com/declare-lab/SAT.git}.
更多
查看译文
关键词
classification,text,semi-supervised,instance-adaptive,self-training
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要