Extreme Multi-label Text Classification

Presented By

Mohan Wu

Introduction

In the field of deep learning, there are times where the label set for text classification is so large that most models give poor results. The authors propose a new model called APLC-XLNet which fine tunes the generalized autoregressive pretrained model (XLNet) by using Adaptive Probabilistic Label Clusters (APLC) to calculate cross entropy loss. This method takes advantage of unbalanced label distributions by forming clusters to reduce training time. The authors experimented on five different datasets and achieved results far better than existing state-of-the-art models.