Research Area:  Machine Learning

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.

Keywords:  

Author(s) Name:  Xiang Zhang, Junbo Zhao, Yann LeCun

Publisher name:  arXiv:1509.01626

DOI:  10.48550/arXiv.1509.01626

Volume Information:  

Paper Link:   https://arxiv.org/abs/1509.01626