Multi-task Coupled Attentions for Category-specific Aspect and Opinion Terms Co-extraction

In aspect-based sentiment analysis, most existing methods focus on either identifying aspect/opinion terms or categorizing pre-extracted aspect terms. Each task by itself only provides partial information to end users. To generate more detailed and structured opinion analysis, we study a finer-grained problem, which we call category-specific aspect and opinion terms extraction. This problem involves identification of aspect and opinion terms within each sentence, as well as categorization of the identified terms at the same time. To this end, we propose an end-to-end multi-task memory network, where aspect/opinion terms extraction for a specific category is considered as a task, and all the tasks are learned jointly by exploring commonalities and relationships among them. We demonstrate stateof-the-art performance of our proposed model on three benchmark datasets.