arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.14724cs.CLcs.AI
收藏

利用动态课程学习改进不平衡文本分类

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

Ping An Technology (Shenzhen) Co., Ltd.(平安科技(深圳)有限公司)

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao

摘要:

预训练语言模型的最新进展提高了文本分类任务的性能。然而,很少有人关注的优先级调度策略的样本在训练过程中。人类获取知识是从简单到复杂的概念逐步进行的,同一材料的难度在不同的学习阶段也会有很大差异。受此启发,本文提出了一种新的基于语言特征和模型容量的自学习动态课程学习(SPDCL)方法。同时,而不是使用静态的课程学习在现有的研究中,我们的SPDCL可以重新排序和重新采样训练数据的难度标准与自适应的从容易到困难的步伐。在多个分类任务上的大量实验表明了SPDCL策略的有效性,特别是对于不平衡数据集。

英文摘要:

Recent advances in pre-trained language models have improved the performance for text classification tasks. However, little attention is paid to the priority scheduling strategy on the samples during training. Humans acquire knowledge gradually from easy to complex concepts, and the difficulty of the same material can also vary significantly in different learning stages. Inspired by this insights, we proposed a novel self-paced dynamic curriculum learning (SPDCL) method for imbalanced text classification, which evaluates the sample difficulty by both linguistic character and model capacity. Meanwhile, rather than using static curriculum learning as in the existing research, our SPDCL can reorder and resample training data by difficulty criterion with an adaptive from easy to hard pace. The extensive experiments on several classification tasks show the effectiveness of SPDCL strategy, especially for the imbalanced dataset.

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。

↑