Global Hierarchical Neural Networks using Hierarchical Softmax
This work addresses classification tasks with hierarchical classes, but it is incremental as it applies an existing technique (hierarchical softmax) to improve performance on standard datasets.
The paper tackled the problem of classification tasks with natural class hierarchies by using hierarchical softmax to create a global hierarchical classifier, resulting in improved macro-F1 and macro-recall across four text classification datasets, with higher micro-accuracy and macro-precision in three datasets.
This paper presents a framework in which hierarchical softmax is used to create a global hierarchical classifier. The approach is applicable for any classification task where there is a natural hierarchy among classes. We show empirical results on four text classification datasets. In all datasets the hierarchical softmax improved on the regular softmax used in a flat classifier in terms of macro-F1 and macro-recall. In three out of four datasets hierarchical softmax achieved a higher micro-accuracy and macro-precision.