arrow
返回

Label prompt for multi-label text classification

delete2022-08-02
delete28
PRE
AI
宋锐 封面图
宋锐 (Rui Song)
Z
Zelong Liu
X
Xingbing Chen
H
Haining An
张
张致齐 (Zhiqi Zhang)
王晓光 封面图
王晓光 (Wang, Xiaoguang) *
徐昊 封面图
徐昊 (Hao Xu)
DOI:10.1007/s10489-022-03896-4delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Multi-label text classification has been widely concerned by scholars due to its contribution to practical applications. One of the key challenges in multi-label text classification is how to extract and leverage the correlation among labels. However, it is quite challenging to directly model the correlations among labels in a complex and unknown label space. In this paper, we propose a Label Prompt Multi-label Text Classification model (LP-MTC), which is inspired by the idea of prompt learning of pre-trained language model. Specifically, we design a set of templates for multi-label text classification, integrate labels into the input of the pre-trained language model, and jointly optimize by Masked Language Models (MLM). In this way, the correlations among labels as well as semantic information between labels and text with the help of self-attention can be captured, and thus the model performance is effectively improved. Extensive empirical experiments on multiple datasets demonstrate the effectiveness of our method. Compared with BERT, LP-MTC improved 3.4% micro-F1 on average over the four public datasets.
Keyword:
Multi-label text classification
BERT
Pormpt learning
Masked language model

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.6K
被引数:
1.7W

机构

J
Jilin University
学者数:
8.7W
论文数: 5.6W
被引数: 8.9K
引用论文

引用论文

Reduced cortical excitatory synapse number in APOE4 mice is associated with increased calcineurin activity
err2017-07-05
err0
errOAAI
errAidan L. Neustadtl; Charisse N. Winston; Maia Parsadanian; Bevan S. Main; Sonia Villapol; Mark P. Burns
err分享
err收藏
Learning multi-label scene classification学习多标签场景分类
err2004-09-01
err2.0K
PREAI
errBoutell, MR; Luo, JB; Shen, XP; Brown, CM
err分享
err收藏
学者 查看更多内容