NLANGP at SemEval-2016 Task 5: Improving Aspect Based Sentiment Analysis using Neural Network Features
Zhiqiang Toh, Jian Su · 2016
This paper describes our system submitted to Aspect Based Sentiment Analysis Task 5 of SemEval-2016. Our system consists of two components: binary classifiers trained using single layer feedforward network for aspect category classification (Slot 1), and sequential labeling classifiers for opinion target extraction (Slot 2). Besides extracting a variety of lexicon features, syntactic features, and cluster features, we explore the use of deep learning systems to provide additional neural network features. Our system achieves the best performances on the English datasets, ranking 1st for four evaluations (Slot 1 for both restaurant and laptop domains, Slot 2, and Slot 1 & 2).