arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.11345cs.CLcs.AI
收藏

基于自学习的短文本分类

Prompt-Learning for Short Text Classification

Yi Zhu, Xinke Zhou, Jipeng Qiang, Yun Li, Yunhao Yuan, Xindong Wu

摘要:

在短文本中,极短的长度、特征稀疏性和高歧义性给分类任务带来了巨大的挑战。近年来,作为一种有效的方法来调整预训练语言模型的特定下游任务,人工学习引起了大量的关注和研究。自动学习背后的主要直觉是将模板插入到输入中,并将文本分类任务转换为等效的完形填空式任务。然而,目前大多数的自动学习方法在进行完形填空式预测时,都是人工扩展标签词或只考虑知识的类名,这在短文本分类任务中不可避免地会产生遗漏和偏差。在本文中,我们提出了一个简单的短文本分类方法,利用基于知识扩展的学习。该方法充分考虑了短文本的特点,在扩展标注词空间时既考虑了短文本本身,又考虑了类名。具体地说,从Probase等开放的知识图谱中检索与短文本中的实体相关的前$N$概念,并通过计算所选概念与类标签之间的距离来进一步细化扩展后的标签词。实验结果表明,该方法与其他微调、自学习和知识自学习方法相比,在三个已知数据集上的性能比现有技术提高了6个精度点。

英文摘要:

In the short text, the extremely short length, feature sparsity, and high ambiguity pose huge challenges to classification tasks. Recently, as an effective method for tuning Pre-trained Language Models for specific downstream tasks, prompt-learning has attracted a vast amount of attention and research. The main intuition behind the prompt-learning is to insert the template into the input and convert the text classification tasks into equivalent cloze-style tasks. However, most prompt-learning methods expand label words manually or only consider the class name for knowledge incorporating in cloze-style prediction, which will inevitably incur omissions and bias in short text classification tasks. In this paper, we propose a simple short text classification approach that makes use of prompt-learning based on knowledgeable expansion. Taking the special characteristics of short text into consideration, the method can consider both the short text itself and class name during expanding label words space. Specifically, the top $N$ concepts related to the entity in the short text are retrieved from the open Knowledge Graph like Probase, and we further refine the expanded label words by the distance calculation between selected concepts and class labels. Experimental results show that our approach obtains obvious improvement compared with other fine-tuning, prompt-learning, and knowledgeable prompt-tuning methods, outperforming the state-of-the-art by up to 6 Accuracy points on three well-known 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。

↑