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

ACL 2018 Zeyang LeiYujiu YangMin YangYi 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... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Sentiment Analysis MR MEAN Accuracy 84.5 # 1
Sentiment Analysis SST-5 Fine-grained classification MEAN Accuracy 51.4 # 7