arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08720cs.LGcs.CLcs.IR
收藏

探索用于长尾多标签文本分类的对比学习研究

Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification

Université Grenoble Alpes(格勒诺布尔大学)

Alexandre Audibert, Aurélien Gauffre, Massih-Reza Amini

AI总结:

针对多标签文本分类中标签关联复杂、数据长尾分布的挑战,本文研究监督对比学习的作用,提出新型对比损失函数,在三个数据集上Micro-F1相当或更优、Macro-F1显著提升。

摘要:

在多标签文本分类(MLTC)中学习有效的表示是自然语言处理(NLP)领域的一项重大挑战。这一挑战源于任务的固有复杂性,由两个关键因素决定:标签之间的复杂关联以及数据普遍存在的长尾分布。为解决这一问题,一种可行的思路是将监督对比学习与经典监督损失函数相结合。尽管对比学习在多分类任务中已展现出优异性能,但其在多标签框架下的作用尚未得到充分研究。本文针对监督对比学习及其在MLTC场景下对表示的影响开展了深入研究,强调了考虑长尾数据分布以构建鲁棒表示空间的重要性,这一思路可有效应对我们发现的与对比学习相关的两个关键挑战:“正样本不足”和“吸引-排斥失衡”。基于这一洞见,我们提出了一种适用于MLTC的新型对比损失函数。在三个多标签数据集上,该函数的Micro-F1得分与其他常用损失函数的结果相当或更优,且Macro-F1得分实现了显著提升。

英文摘要:

Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections between labels and the widespread long-tailed distribution of the data. To overcome this issue, one potential approach involves integrating supervised contrastive learning with classical supervised loss functions. Although contrastive learning has shown remarkable performance in multi-class classification, its impact in the multi-label framework has not been thoroughly investigated. In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context. We emphasize the importance of considering long-tailed data distributions to build a robust representation space, which effectively addresses two critical challenges associated with contrastive learning that we identify: the "lack of positives" and the "attraction-repulsion imbalance". Building on this insight, we introduce a novel contrastive loss function for MLTC. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions, and demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets.

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。

↑