Character-level Convolutional Networks for Text Classification

The paper offers an empirical exploration of applying character-level convolutional networks (ConvNets) to text classification, treating text as a raw sequence of characters rather than words. To evaluate this approach at scale, the authors construct several large-scale datasets on which the character-level models can be trained and tested.

The experiments show that character-level ConvNets can achieve state-of-the-art or competitive results on these datasets. The authors benchmark them against traditional models such as bag-of-words, n-grams, and their TF-IDF variants, as well as deep learning models including word-based ConvNets and recurrent neural networks, positioning character-level modeling as a viable alternative for text classification.