Label prompt for multi-label text classification

TL;DR

This paper introduces LM-MTC, a novel multi-label text classification model that leverages label masking and pre-trained language models to implicitly learn label correlations, improving generalization across datasets.

Contribution

The paper proposes a new label masking approach combined with pre-trained language models for multi-label classification, capturing label correlations without explicit modeling.

Findings

Effective in capturing label correlations

Improves generalization on multiple datasets

Outperforms existing methods

Abstract

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.