arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05231cs.CLcs.LG
收藏

基于自监督正则化的文本分类

Self-supervised Regularization for Text Classification

Shanghai Jiao Tong University(上海交通大学);Northeastern University(东北大学);UC San Diego(加利福尼亚大学圣迭戈分校)

Meng Zhou, Zechen Li, Pengtao Xie

摘要:

文本分类是一个被广泛研究的问题,有着广泛的应用。在许多现实问题中,用于训练分类模型的文本数量是有限的,这使得这些模型容易过拟合。为了解决这个问题,我们提出了SSL-Reg,一种基于自监督学习(SSL)的数据依赖正则化方法。SSL是一种无监督学习方法,它在输入数据上定义辅助任务,而不使用任何人类提供的标签,并通过解决这些辅助任务来学习数据表示。在SSL-Reg中,监督分类任务和无监督SSL任务同时执行。SSL任务是无监督的,它纯粹是在输入文本上定义的,不使用任何人工提供的标签。使用SSL任务训练模型可以防止模型过度拟合到分类任务中有限数量的类标签。在17个文本分类数据集上的实验证明了该方法的有效性。

英文摘要:

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL is an unsupervised learning approach which defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human-provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method.

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。

↑