A Joint Model for Target-Oriented Opinion Words Extraction and Sentiment Classification

Target-oriented opinion word extraction and aspect-level sentiment classification are two highly relevant tasks in aspect-based sentiment analysis. Previous studies tend to separate them and focus on one of the tasks, which ignore the connection between opinion word extraction and sentiment classification, and result in the waste of useful connection information. In this paper, we propose a co-extraction model, in which the two tasks are formulated as a sequence labeling problem. The model involves two stacked Bi-LSTM modules and an information interaction component to generate all opinion-polarity pairs of the input sentences simultaneously. The experimental results show that our model achieves advanced results in target opinion word-polarity co-extraction. The performance of both tasks is stronger than the baseline, and the model is of low complexity and high operational efficiency.