Light-Weighted CNN for Text Classification

04/16/2020
by   Ritu Yadav, et al.
10

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2016

Xception: Deep Learning with Depthwise Separable Convolutions

We present an interpretation of Inception modules in convolutional neura...
research
03/31/2018

In-depth Question classification using Convolutional Neural Networks

Convolutional neural networks for computer vision are fairly intuitive. ...
research
03/11/2019

An Innovative Word Encoding Method For Text Classification Using Convolutional Neural Network

Text classification plays a vital role today especially with the intensi...
research
06/05/2018

Adapting Neural Text Classification for Improved Software Categorization

Software Categorization is the task of organizing software into groups t...
research
09/29/2020

Natcat: Weakly Supervised Text Classification with Naturally Annotated Datasets

We seek to improve text classification by leveraging naturally annotated...
research
06/18/2017

Towards the Improvement of Automated Scientific Document Categorization by Deep Learning

This master thesis describes an algorithm for automated categorization o...

Please sign up or login with your details

Forgot password? Click here to reset