Hands-On Natural Language Processing with Python

Deep learning for multi-label classification

In the paper on Large-scale Multi-label Text Classification – Revisiting Neural Networks (https://arxiv.org/abs/1312.5419), Nam et al. approaches this problem by using a deep multi-layer perceptron (MLP) with a hidden layer and output units producing scores for the labels. They use a label predictor which converts the label scores from the deep network to binary classes using thresholding based on a rank loss function. The details of this approach can be found in the aforementioned paper.

The following diagram illustrates this approach:

Approach for multi-label classification

In the preceding diagram, ...