arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.02810cs.CL
收藏

科技文献的层次多标号分类

Hierarchical Multi-Label Classification of Scientific Documents

University of Illinois Chicago(伊利诺伊大学芝加哥分校)

Mobashir Sadat, Cornelia Caragea

摘要:

自动主题分类已被广泛研究,以帮助管理和索引的数字收集的科学文献。随着近年来出现的大量主题,有必要将它们按层次排列。因此,自动分类系统需要能够分级地对文档进行分类。此外,每篇论文往往被分配到一个以上的相关主题。例如,一篇论文可以被分配到层次树中的几个主题。在本文中,我们介绍了一个新的数据集,用于科学论文的分层多标签文本分类(HMLTC),称为SciHTC,它包含来自ACM CCS树的186,160篇论文和1,233个类别。我们为HMLTC建立了强大的基线,并提出了一种多任务学习方法,用于主题分类,关键字标记作为辅助任务。我们的最佳模型达到了34.57%的Macro-F1得分,这表明该数据集为分层科学主题分类提供了重要的研究机会。我们在Github上提供数据集和代码。

英文摘要:

Automatic topic classification has been studied extensively to assist managing and indexing scientific documents in a digital collection. With the large number of topics being available in recent years, it has become necessary to arrange them in a hierarchy. Therefore, the automatic classification systems need to be able to classify the documents hierarchically. In addition, each paper is often assigned to more than one relevant topic. For example, a paper can be assigned to several topics in a hierarchy tree. In this paper, we introduce a new dataset for hierarchical multi-label text classification (HMLTC) of scientific papers called SciHTC, which contains 186,160 papers and 1,233 categories from the ACM CCS tree. We establish strong baselines for HMLTC and propose a multi-task learning approach for topic classification with keyword labeling as an auxiliary task. Our best model achieves a Macro-F1 score of 34.57% which shows that this dataset provides significant research opportunities on hierarchical scientific topic classification. We make our dataset and code available on Github.

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。

↑