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 2306.02175cs.CL
收藏

TART:使用任务自适应参考变换改进少样本文本分类

TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation

Virginia Tech(弗吉尼亚理工大学);Microsoft(微软)

Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu

AI总结:

针对少样本文本分类中现有元学习方法难以区分语义相似类的问题,提出TART网络,通过任务自适应度量空间的类原型变换与判别正则化增强泛化,在四个基准数据集上取得SOTA,20 Newsgroups上1/5-shot分别提升7.4%、5.4%。

摘要:

元学习已成为解决少样本文本分类并取得最优性能的热门技术。然而,现有方法的性能严重依赖支持集的类间方差。因此,当采样类的语义差异明显时,这类方法在任务上表现良好,但无法区分语义相似的类。本文提出了一种新颖的任务自适应参考变换(Task-Adaptive Reference Transformation,TART)网络,旨在通过在任务自适应度量空间中将类原型变换为每个类的固定参考点来增强泛化能力。为了进一步最大化任务自适应度量空间中变换后原型之间的差异,TART在变换后的原型之间引入了判别性参考正则化。我们在四个基准数据集上开展了大量实验,结果表明我们的方法在所有数据集上均明显优于现有最优模型。具体而言,在20 Newsgroups数据集上,我们的模型在1样本和5样本分类任务中分别比现有最优方法高出7.4%和5.4%。

英文摘要:

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.

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。

↑