SGM: Sequence Generation Model for Multi-label Classification
This addresses the problem of ignoring label correlations and variable text contributions in multi-label classification for NLP, but appears incremental as it builds on sequence generation models.
The paper tackles multi-label classification by framing it as a sequence generation problem, using a novel decoder structure, and reports that the method outperforms previous work by a substantial margin.
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.