Large-Scale Multi-label Text Classification - Revisiting Neural Networks
Jinseok Nam, Jungi Kim, Eneldo Loza Mencía, Iryna Gurevych, Johannes Fürnkranz · 2013
Abstract. Neural networks have recently been proposed for multi-label classi-fication because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural net-work (NN) architecture that aims at minimizing pairwise ranking error. Instead, we propose to use a comparably simple NN approach with recently proposed learning techniques for large-scale multi-label text classification tasks. In partic-ular, we show that BP-MLL’s ranking loss minimization can be efficiently and effectively replaced with the commonly used cross entropy error function, and demonstrate that several advances in neural network training that have been de-veloped in the realm of deep learning can be effectively employed in this setting. Our experimental results show that simple NN models equipped with advanced techniques such as rectified linear units, dropout, and AdaGrad perform as well as or even outperform state-of-the-art approaches on six large-scale textual datasets with diverse characteristics. 1