SLCNN: Sentence-Level Convolutional Neural Network for Text Classification
This work addresses text classification in NLP, particularly for longer documents, but appears incremental as it builds on existing CNN methods with a novel sentence-level approach.
The paper tackled text classification by proposing a sentence-level convolutional neural network (SLCNN) that uses a three-dimensional tensor representation to analyze positional and adjacent sentence information, resulting in better performance, especially on longer documents, compared to state-of-the-art models.
Text classification is a fundamental task in natural language processing (NLP). Several recent studies show the success of deep learning on text processing. Convolutional neural network (CNN), as a popular deep learning model, has shown remarkable success in the task of text classification. In this paper, new baseline models have been studied for text classification using CNN. In these models, documents are fed to the network as a three-dimensional tensor representation to provide sentence-level analysis. Applying such a method enables the models to take advantage of the positional information of the sentences in the text. Besides, analysing adjacent sentences allows extracting additional features. The proposed models have been compared with the state-of-the-art models using several datasets. The results have shown that the proposed models have better performance, particularly in the longer documents.