Hierarchical Interactive Network for joint aspect extraction and sentiment classification

作者：

Highlights：

• Aspect-Based Sentiment is an emerging area in both research and practice.

• We proposed a novel span-based multi-task learning framework to enhance the correlations between two subtasks.

• Extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed method.

摘要

•Aspect-Based Sentiment is an emerging area in both research and practice.•We proposed a novel span-based multi-task learning framework to enhance the correlations between two subtasks.•Extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed method.

论文关键词：Aspect extraction,Sentiment classification,Hierarchical Interactive Network,Span-based model

论文评审过程：Received 2 May 2022, Revised 26 August 2022, Accepted 27 August 2022, Available online 2 September 2022, Version of Record 16 September 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109825