Target-oriented Opinion Words Extraction via graph convolutional network

Abstract

Target-oriented opinion word extraction (TOWE) is a sequence labelling subtask of aspect-level sentiment analysis (ABSA), which aims to extract corresponding opinion words for a given sentence and opinion target. In view of the existing related work, the structural information of sentences is not fully considered. In this study, we explore the integration of neural network and dependency tree to handle the TOWE and propose a model based on graph convolution network (GCN). The model uses the long short-term memory network (LSTM) to learn the semantic features of sentences. On this basis, the model uses the GCN to model the sentence structure through dependency tree and capture the syntactic dependency relationship between the target word and the opinion word. The experimental results show that GCN can effectively improve the performance of TOWE. The F1 values of the model on the semeval-rest14 and semeval-laptop14 reached 82.60% and 74.45%.