arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01560cs.CLcs.AI
收藏

面向低资源文本分类的词角色选择性文本增强

Selective Text Augmentation with Word Roles for Low-Resource Text Classification

Shanghai University of Finance and Economics(上海财经大学)

Biyang Guo, Songqiao Han, Hailiang Huang

摘要:

数据增强技术被广泛应用于文本分类任务中,以提高分类器的性能,特别是在低资源的情况下。大多数以前的方法进行文本增强没有考虑文本中的单词的不同功能,这可能会产生不满意的样本。不同的词在文本分类中可能扮演不同的角色,这启发我们有策略地选择合适的角色进行文本增强。在这项工作中,我们首先确定文本中的词和文本类别之间的关系,从统计相关性和语义相似性的角度,然后利用它们划分为四个角色的话-黄金,风险,奖金,和琐碎的话,这对文本分类具有不同的功能。基于这些词的角色,我们提出了一种新的增强技术,称为STA(选择性文本增强),不同的文本编辑操作有选择地应用于特定的角色的话。STA可以生成多样且相对干净的样本,同时保留原始的核心语义,并且实现起来也相当简单。在5个基准低资源文本分类数据集上的大量实验表明,STA产生的增强样本成功地提高了分类模型的性能,其性能显著优于以前的非选择性方法,包括两种基于大语言模型的技术。跨数据集实验进一步表明,STA可以帮助分类器更好地推广到其他数据集比以前的方法。

英文摘要:

Data augmentation techniques are widely used in text classification tasks to improve the performance of classifiers, especially in low-resource scenarios. Most previous methods conduct text augmentation without considering the different functionalities of the words in the text, which may generate unsatisfactory samples. Different words may play different roles in text classification, which inspires us to strategically select the proper roles for text augmentation. In this work, we first identify the relationships between the words in a text and the text category from the perspectives of statistical correlation and semantic similarity and then utilize them to divide the words into four roles -- Gold, Venture, Bonus, and Trivial words, which have different functionalities for text classification. Based on these word roles, we present a new augmentation technique called STA (Selective Text Augmentation) where different text-editing operations are selectively applied to words with specific roles. STA can generate diverse and relatively clean samples, while preserving the original core semantics, and is also quite simple to implement. Extensive experiments on 5 benchmark low-resource text classification datasets illustrate that augmented samples produced by STA successfully boost the performance of classification models which significantly outperforms previous non-selective methods, including two large language model-based techniques. Cross-dataset experiments further indicate that STA can help the classifiers generalize better to other datasets than previous methods.

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。

↑