Primitive Operation Aggregation Algorithms for Improving Taxonomies for Large-Scale Hierarchical Classifiers
Naive implementations of hierarchical classifiers that classify documents into large-scale taxonomy structures may face the contradiction between relevancy and efficiency performances. To address this problem, the authors focused on taxonomy modification algorithms for gradually improving the relevance performances of large-scale hierarchical classifiers. They developed four taxonomy modification algorithms that aggregate primitive operations before investigating hierarchical relevance performances. All but one produced taxonomy sequences that generate classifiers exhibiting practical efficiencies.