Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level
This work provides a comparative analysis for researchers in natural language processing, but it is incremental as it builds on prior CNN methods.
The paper compares shallow word-level CNNs to deep character-level CNNs for text categorization, finding that the shallow word-level CNNs achieve better error rates on eight datasets, though with more parameters and storage but faster computation.
This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNNs achieve better error rates than the error rates reported in Conneau et al., though the results should be interpreted with some consideration due to the unique pre-processing of Conneau et al. The shallow word-level CNN uses more parameters and therefore requires more storage than the deep character-level CNN; however, the shallow word-level CNN computes much faster.