arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.12653cs.CLcs.LG
收藏

SAT:基于简单实例自适应训练的半监督文本分类

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

Singapore University of Technology and Design(新加坡科技设计大学)

Hui Chen, Wei Han, Soujanya Poria

摘要:

自训练方法在近年来已经被探索,并且在改进半监督学习方面表现出很好的性能。本文提出了一种简单的实例自适应自训练方法(SAT)用于半监督文本分类。SAT首先为每个未标记的数据生成两个增强视图,然后训练元学习器基于原始视图和增强视图之间的相似性自动识别增强的相对强度。将弱增强视图馈送到模型以产生伪标签,并且使用强增强视图来训练模型以预测相同的伪标签。我们在三个文本分类数据集上进行了广泛的实验和分析,发现与现有的半监督学习方法相比,在不同大小的标记训练数据下,SAT始终表现出具有竞争力的性能。我们的代码可以在\url{https://github.com/declare-lab/SAT.git}中找到。

英文摘要:

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}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑