Towards Using Reranking in Hierarchical Classification

We consider the use of reranking as a way to relax typical independence assumptions often made in hierarchical multilabel classification. Our reranker is based on (i) an algorithm that generates promising k-best classification hypotheses from the output of local binary classifiers that classify nodes of a target tree-shaped hierarchy; and (ii) a tree kernel-based reranker applied to the classification tree associated with the hypotheses above. We carried out a number of experiments with this model on the Reuters corpus: we firstly show the potential of our algorithm by computing the oracle classification accuracy. This demonstrates that there is a significant room for potential improvement of the hierarchical classifier. Then, we measured the accuracy achieved by the reranker, which shows a significant performance improvement over the baseline.