Multiple Perspective Attention Based on Double BiLSTM for Aspect and Sentiment Pair Extract

Abstract Aspect category sentiment analysis has attracted increasing attention because of its outstanding performance in mining the fine-grained sentiment expression of users. In recent years, a new aspect category and sentiment pair extraction (ASPE) task has been proposed to simultaneously extract aspect categories and sentiment pairs. Most existing research works are designed in a two step pipeline, that is, they first perform aspect category detection, and subsequently conduct aspect category sentiment analysis. However, the pipeline method can clearly lead to error propagation from previous step. In this work, we propose a new framework for multiple perspective attention based on double BiLSTM with a novel joint strategy for ASPE to alleviate the accumulation of errors in the pipeline method. The experimental results on benchmark datasets SemEval and BDCI-2018 demonstrate the effectiveness of the proposed approach in terms of both accuracy and explainability for the ASPE task.