Combining Convolution and Recursive Neural Networks for Sentiment Analysis
This work addresses sentiment analysis for natural language processing applications, but it is incremental as it builds on existing neural network methods.
The paper tackles sentence-level sentiment analysis by combining Convolutional and Recursive Neural Networks into a new architecture and using transfer learning from a large dataset to improve word embeddings, resulting in models that outperform recent Convolutional and Recursive Neural Networks and achieve comparable performance with state-of-the-art systems on the Stanford Sentiment Treebank.
This paper addresses the problem of sentence-level sentiment analysis. In recent years, Convolution and Recursive Neural Networks have been proven to be effective network architecture for sentence-level sentiment analysis. Nevertheless, each of them has their own potential drawbacks. For alleviating their weaknesses, we combined Convolution and Recursive Neural Networks into a new network architecture. In addition, we employed transfer learning from a large document-level labeled sentiment dataset to improve the word embedding in our models. The resulting models outperform all recent Convolution and Recursive Neural Networks. Beyond that, our models achieve comparable performance with state-of-the-art systems on Stanford Sentiment Treebank.