arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07349cs.CLcs.LG
收藏

MATCH:大型层次结构中的元数据感知文本分类

MATCH: Metadata-Aware Text Classification in A Large Hierarchy

Univ. of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院);Facebook AI(脸书人工智能研究院)

Yu Zhang, Zhihong Shen, Yuxiao Dong, Kuansan Wang, Jiawei Han

AI总结:

本文针对大型标签层次结构中的多标签文本分类问题,提出端到端框架MATCH,同时利用元数据和标签层次结构信息,通过预训练嵌入和全连接注意力机制及父标签正则化方法,在两个大规模数据集上显著优于现有深度学习基线。

摘要:

多标签文本分类是指从标签集中为每个给定文档分配其最相关标签的问题。通常,在现实应用中,给定文档的元数据和标签的层次结构是可用的。然而,大多数现有研究仅关注对文本信息进行建模,少数尝试利用元数据或层次结构信号,但未同时利用两者。在本文中,我们通过形式化大型标签层次结构(例如,具有数万个标签)中的元数据感知文本分类问题来弥合这一差距。为了解决这个问题,我们提出了MATCH解决方案——一个端到端框架,同时利用元数据和层次结构信息。为了纳入元数据,我们在同一空间中预训练文本和元数据的嵌入,并利用全连接注意力来捕获它们之间的相互关系。为了利用标签层次结构,我们提出了不同的方法,通过父标签来正则化每个子标签的参数和输出概率。在两个具有大规模标签层次结构的海量文本数据集上的广泛实验证明了MATCH相对于最先进的深度学习基线的有效性。

英文摘要:

Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set. Commonly, the metadata of the given documents and the hierarchy of the labels are available in real-world applications. However, most existing studies focus on only modeling the text information, with a few attempts to utilize either metadata or hierarchy signals, but not both of them. In this paper, we bridge the gap by formalizing the problem of metadata-aware text classification in a large label hierarchy (e.g., with tens of thousands of labels). To address this problem, we present the MATCH solution -- an end-to-end framework that leverages both metadata and hierarchy information. To incorporate metadata, we pre-train the embeddings of text and metadata in the same space and also leverage the fully-connected attentions to capture the interrelations between them. To leverage the label hierarchy, we propose different ways to regularize the parameters and output probability of each child label by its parents. Extensive experiments on two massive text datasets with large-scale label hierarchies demonstrate the effectiveness of MATCH over state-of-the-art deep learning baselines.

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。

↑