A Comparative Study of Neural Network Models for Sentence Classification
This work provides practical guidance for applying neural networks in sentence classification, but it is incremental as it compares existing methods.
The paper compared four neural network models on English and Vietnamese sentence classification datasets, finding that convolutional networks outperformed models with hand-crafted features on English and beat strong baselines on Vietnamese.
This paper presents an extensive comparative study of four neural network models, including feed-forward networks, convolutional networks, recurrent networks and long short-term memory networks, on two sentence classification datasets of English and Vietnamese text. We show that on the English dataset, the convolutional network models without any feature engineering outperform some competitive sentence classifiers with rich hand-crafted linguistic features. We demonstrate that the GloVe word embeddings are consistently better than both Skip-gram word embeddings and word count vectors. We also show the superiority of convolutional neural network models on a Vietnamese newspaper sentence dataset over strong baseline models. Our experimental results suggest some good practices for applying neural network models in sentence classification.