Export Reviews, Discussions, Author Feedback and Meta-Reviews

The paper presents a character-level convolutional network architecture and applies it to eight text classification problems on large datasets that the authors construct. It also presents comparative results from several word-based deep NN models as well as bag-of-ngrams models. The character-level ConvNets outperform word-based models on four out of eight datasets, when word-based data augmentation is used. The clarity and quality of writing are ok but the presentation of the method and results could have been much more clear. There are numerous grammatical and spelling errors.