Character-level Convolutional Networks for Text Classification

TL;DR

This paper empirically evaluates character-level convolutional networks for text classification, demonstrating their competitive performance against traditional and deep learning models on large datasets.

Contribution

It provides a comprehensive empirical analysis showing that character-level ConvNets can achieve state-of-the-art results in text classification tasks.

Findings

Character-level ConvNets achieve competitive results.

They outperform traditional models like bag of words and n-grams.

They are comparable to word-based ConvNets and RNNs.

Abstract

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.