Convolutional Neural Networks for Sentence Classification
This work addresses the problem of sentence classification for natural language processing applications, such as sentiment analysis and question classification, with incremental improvements.
The authors tackled sentence-level classification tasks by using convolutional neural networks (CNNs) with pre-trained word vectors, achieving excellent results on multiple benchmarks and improving state-of-the-art on 4 out of 7 tasks.
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.