Combining Convolution and Recursive Neural Networks for Sentiment Analysis

Abstract

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.

8 pages, 3 figures, Proceedings of the Eighth International Symposium on Information and Communication Technology. ACM, 2017

References in corpus (12)

• A guide to convolution arithmetic for deep learning
• Convolutional Neural Networks for Sentence Classification
• Exploring the Limits of Language Modeling
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• A Convolutional Neural Network for Modelling Sentences
• Learning to Generate Reviews and Discovering Sentiment
• Knowledge Matters: Importance of Prior Information for Optimization
• When Are Tree Structures Necessary for Deep Learning of Representations?
• Towards Universal Paraphrastic Sentence Embeddings
• Multiplicative LSTM for sequence modelling
• Deep Learning with Dynamic Computation Graphs
• Multichannel Variable-Size Convolution for Sentence Classification