arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.12965cs.CLcs.AIcs.LG
收藏

文本分类中的类别分布偏移:一项综述

Text Classification Under Class Distribution Shift: A Survey

Department of Computer Science, University of Bucharest(计算机科学系,布加勒斯特大学)

Adriana Valentina Costache, Silviu Florin Gheorghe, Eduard Gabriel Poesina, Paul Irofti, Radu Tudor Ionescu

AI总结:

本文综述了文本分类中类别分布偏移问题,探讨了开放集学习、零样本学习等方法,并提出了连续学习作为解决分布偏移的潜在方案。

摘要:

机器学习(ML)模型的基本假设是训练数据和测试数据均采样自同一分布。然而,在日常实践中,这一假设往往被打破,即测试数据的分布会随时间变化,这阻碍了传统ML模型的应用。文本分类领域自然会出现分布偏移,因为人们总在讨论新话题。为此,我们综述了研究开放集文本分类及相关任务的文章。我们根据定义此类分布偏移的约束条件和相应的问题设定,将该领域的方法划分为学习与Universum、零样本学习和开放集学习。我们随后讨论了每种问题设置的主要缓解方法。我们进一步确定了几个未来研究方向,旨在推动边界超越当前的最先进水平。最后,我们解释了连续学习如何解决许多由变化的类别分布引起的问题。我们维护了一个相关论文列表,网址为https://github.com/Eduard6421/Open-Set-Survey。

英文摘要:

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data changes over time, which hinders the application of conventional ML models. One domain where the distribution shift naturally occurs is text classification, since people always find new topics to discuss. To this end, we survey research articles studying open-set text classification and related tasks. We divide the methods in this area based on the constraints that define the kind of distribution shift and the corresponding problem formulation, i.e. learning with the Universum, zero-shot learning, and open-set learning. We next discuss the predominant mitigation approaches for each problem setup. We further identify several future work directions, aiming to push the boundaries beyond the state of the art. Finally, we explain how continual learning can solve many of the issues caused by the shifting class distribution. We maintain a list of relevant papers at https://github.com/Eduard6421/Open-Set-Survey.

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。

↑