In-depth Question classification using Convolutional Neural Networks

TL;DR

This paper explores the application of convolutional neural networks to question classification, proposing a structure that improves accuracy and efficiency in categorizing questions into topics and sub-topics.

Contribution

It introduces a CNN-based architecture tailored for question classification, with a two-stage process for broad and fine-grained categorization, enhancing interpretability and performance.

Findings

Effective CNN model for question topic prediction

Improved classification accuracy over baseline methods

Faster training times compared to traditional approaches

Abstract

Convolutional neural networks for computer vision are fairly intuitive. In a typical CNN used in image classification, the first layers learn edges, and the following layers learn some filters that can identify an object. But CNNs for Natural Language Processing are not used often and are not completely intuitive. We have a good idea about what the convolution filters learn for the task of text classification, and to that, we propose a neural network structure that will be able to give good results in less time. We will be using convolutional neural networks to predict the primary or broader topic of a question, and then use separate networks for each of these predicted topics to accurately classify their sub-topics.