SGM: Sequence Generation Model for Multi-label Classification

TL;DR

This paper introduces a sequence generation approach for multi-label classification in NLP, effectively capturing label correlations and identifying key words for each label, leading to improved performance.

Contribution

It proposes a novel sequence generation model with a new decoder structure specifically designed for multi-label classification tasks.

Findings

Outperforms previous methods significantly

Captures label correlations effectively

Automatically identifies informative words for labels

Abstract

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations between labels. Besides, different parts of the text can contribute differently for predicting different labels, which is not considered by existing models. In this paper, we propose to view the multi-label classification task as a sequence generation problem, and apply a sequence generation model with a novel decoder structure to solve it. Extensive experimental results show that our proposed methods outperform previous work by a substantial margin. Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.