Light-Weighted CNN for Text Classification

16 Apr 2020  ·  Ritu Yadav ·

For management, documents are categorized into a specific category, and to do these, most of the organizations use manual labor. In today's automation era, manual efforts on such a task are not justified, and to avoid this, we have so many software out there in the market. However, efficiency and minimal resource consumption is the focal point which is also creating a competition. The categorization of such documents into specified classes by machine provides excellent help. One of categorization technique is text classification using a Convolutional neural network(TextCNN). TextCNN uses multiple sizes of filters, as in the case of the inception layer introduced in Googlenet. The network provides good accuracy but causes high memory consumption due to a large number of trainable parameters. As a solution to this problem, we introduced a whole new architecture based on separable convolution. The idea of separable convolution already exists in the field of image classification but not yet introduces to text classification tasks. With the help of this architecture, we can achieve a drastic reduction in trainable parameters.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Document Text Classification Tobacco-3482 Optimized Text CNN Accuracy 46 # 1
Training time (hours) 2 # 1
Document Text Classification Tobacco-3482 Lightweight TextCNN with Dual Optimizer Accuracy 43.5 # 2
Training time (hours) 0.43 # 3
Document Text Classification Tobacco-3482 Lightweight Text CNN Accuracy 42 # 3
Training time (hours) 1 # 2
Document Text Classification Tobacco small-3482 Lightweight TextCNN with Dual Optimizer Accuracy 83 # 2
Training time (min) 2 # 3
Document Text Classification Tobacco small-3482 Lightweight Text CNN Accuracy 82.5 # 3
Training time (min) 5 # 2
Document Text Classification Tobacco small-3482 Optimized Text CNN Accuracy 84 # 1
Training time (min) 9 # 1

Methods