A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification

ACL 2018  ·  Zeyang Lei, Yujiu Yang, Min Yang, Yi Liu ·

Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge. In this paper, we propose a Multi-sentiment-resource Enhanced Attention Network (MEAN) to alleviate the problem by integrating three kinds of sentiment linguistic knowledge (e.g., sentiment lexicon, negation words, intensity words) into the deep neural network via attention mechanisms... By using various types of sentiment resources, MEAN utilizes sentiment-relevant information from different representation subspaces, which makes it more effective to capture the overall semantics of the sentiment, negation and intensity words for sentiment prediction. The experimental results demonstrate that MEAN has robust superiority over strong competitors. read more

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sentiment Analysis MR MEAN Accuracy 84.5 # 3
Sentiment Analysis SST-5 Fine-grained classification MEAN Accuracy 51.4 # 12

Methods


No methods listed for this paper. Add relevant methods here