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 2106.10076cs.CLcs.AI
收藏

多标签文本分类的标签提示

Label prompt for multi-label text classification

Jilin University(吉林大学)

Rui Song, Xingbing Chen, Zelong Liu, Haining An, Zhiqi Zhang, Xiaoguang Wang, Hao Xu

摘要:

多标签文本分类的关键问题之一是如何利用标签之间的相关性。然而,在复杂和未知的标签空间中直接建模标签之间的相关性是非常具有挑战性的。受语言模型完形填空题思想的启发,本文提出了一种标签掩码多标签文本分类模型(LM-MTC)。LM-MTC能够通过预训练语言模型的强大能力来捕获标签之间的隐式关系。在此基础上,我们为每个潜在的标签分配不同的标记,并以一定的概率随机屏蔽标记,以建立基于标签的屏蔽语言模型(MLM)。我们将MTC和MLM一起进行训练,进一步提高了模型的泛化能力。在多个数据集上的大量实验证明了该方法的有效性。

英文摘要:

One of the key problems in multi-label text classification is how to take advantage of the correlation among labels. However, it is very challenging to directly model the correlations among labels in a complex and unknown label space. In this paper, we propose a Label Mask multi-label text classification model (LM-MTC), which is inspired by the idea of cloze questions of language model. LM-MTC is able to capture implicit relationships among labels through the powerful ability of pre-train language models. On the basis, we assign a different token to each potential label, and randomly mask the token with a certain probability to build a label based Masked Language Model (MLM). We train the MTC and MLM together, further improving the generalization ability of the model. A large number of experiments on multiple datasets demonstrate the effectiveness of our method.

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。

↑