arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00364cs.CL
收藏

文本分类综述:从浅层学习到深度学习

A Survey on Text Classification: From Shallow to Deep Learning

Beihang University(北京航空航天大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校);University of Leeds(利兹大学);Lehigh University(里海大学)

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, Lifang He

摘要:

文本分类是自然语言处理中最基本、最关键的任务。由于深度学习取得了前所未有的成功,过去十年来,这一领域的研究激增。文献中提出了许多方法、数据集和评价指标,因此需要进行全面和更新的调查。本文通过回顾1961年至2021年的最新方法填补了这一空白,重点关注从传统模型到深度学习的模型。我们根据文本内容和用于特征提取和分类的模型建立了一个文本分类系统。然后,我们将详细讨论这些类别中的每一个,处理支持预测测试的技术发展和基准数据集。本调查还提供了不同技术之间的全面比较,以及各种评估指标的优缺点。最后,总结了本研究的主要意义、未来研究方向和面临的挑战。

英文摘要:

Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021, focusing on models from traditional models to deep learning. We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification. We then discuss each of these categories in detail, dealing with both the technical developments and benchmark datasets that support tests of predictions. A comprehensive comparison between different techniques, as well as identifying the pros and cons of various evaluation metrics are also provided in this survey. Finally, we conclude by summarizing key implications, future research directions, and the challenges facing the research area.

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。

↑