A span-based model for aspect terms extraction and aspect sentiment classification

Sentiment analysis is a field of natural language processing, which is used to identify and extract opinions and attitudes from text. Aspect-based sentiment analysis aims to extract aspect terms and predict sentiment categories of the opinion aspects. It includes two subtasks: aspect terms extraction and aspect sentiment classification. However, previous studies regarded them as two independent tasks and solve them, respectively, which has limitations for practical application. In this paper, we combine the requirements of two subtasks to propose a new aspect-based sentiment analysis framework based on span, which is a simple and effective joint model to generate all aspects and corresponding sentiment polarities of the input sentences. Specifically, dual gated recurrent units which are used to extract the respective representation of each task can process sequence information better, and an interaction layer which is used to consider the relationship between the representations. Experiments on three benchmark datasets show that the proposed framework outperforms the state-of-the-art baseline models.