HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization
This work addresses hierarchical text classification, an incremental improvement over existing methods for tasks like document categorization.
The paper tackles the limitations of the state-of-the-art HiAGM model in hierarchical text classification by proposing HTCInfoMax, which uses information maximization to filter irrelevant label information and improve label representations, achieving effectiveness on two benchmark datasets.
The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. First, it correlates each text sample with all labels in the dataset which contains irrelevant information. Second, it does not consider any statistical constraint on the label representations learned by the structure encoder, while constraints for representation learning are proved to be helpful in previous work. In this paper, we propose HTCInfoMax to address these issues by introducing information maximization which includes two modules: text-label mutual information maximization and label prior matching. The first module can model the interaction between each text sample and its ground truth labels explicitly which filters out irrelevant information. The second one encourages the structure encoder to learn better representations with desired characteristics for all labels which can better handle label imbalance in hierarchical text classification. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed HTCInfoMax.