Character-Based Text Classification using Top Down Semantic Model for Sentence Representation
This work addresses the challenge of applying deep learning effectively in text classification, especially for smaller datasets where it often underperforms compared to simpler methods.
The paper tackles the problem of text classification by proposing a character-based model (TDSM) that combines word-level and sentence-level semantics, achieving better performance than other CNN models across seven datasets with only 1% of their parameters and outperforming traditional linear models on small datasets.
Despite the success of deep learning on many fronts especially image and speech, its application in text classification often is still not as good as a simple linear SVM on n-gram TF-IDF representation especially for smaller datasets. Deep learning tends to emphasize on sentence level semantics when learning a representation with models like recurrent neural network or recursive neural network, however from the success of TF-IDF representation, it seems a bag-of-words type of representation has its strength. Taking advantage of both representions, we present a model known as TDSM (Top Down Semantic Model) for extracting a sentence representation that considers both the word-level semantics by linearly combining the words with attention weights and the sentence-level semantics with BiLSTM and use it on text classification. We apply the model on characters and our results show that our model is better than all the other character-based and word-based convolutional neural network models by \cite{zhang15} across seven different datasets with only 1\% of their parameters. We also demonstrate that this model beats traditional linear models on TF-IDF vectors on small and polished datasets like news article in which typically deep learning models surrender.