Interactive Rule Attention Network for Aspect-Level Sentiment Analysis

Abstract

Aspect-level sentiment analysis is a fundamental task in NLP, and it aims to predict the sentiment polarity of each specific aspect term in a given sentence. Recent researches show that the fine-grained sentiment analysis for aspect-level has become a research hotspot. However, previous work did not consider the influence of grammatical rules on aspect-level sentiment analysis. In addition, attention mechanism is too simple to learn attention information from context and target interactively. Therefore, we propose an interactive rule attention network (Iran) for aspect-level sentiment analysis. Iran not only designs a grammar rule encoder, which simulates the grammatical functions at the sentence by standardizing the output of adjacent positions, but also constructs an interaction attention network to learn attention information from context and target. Experimental results on SemEval 2014 Dataset and ACL 2014 Twitter Dataset demonstrate Iran can learn effective features and obtain superior performance over the baseline models.