2021/11/18 by Hongjiang Jing, Jing, Hongjiang, Zuchao Li +5 · 2 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial intelligence #Benchmark (surveying) #Computation and Language (cs.CL) #Computer science #Data mining #Encoder #FOS: Computer and information sciences #Joint (building) #Machine learning #Pipeline (software) #Robustness (evolution) #Sentiment Analysis and Opinion Mining #Sentiment analysis #Task (project management) #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2111.09634
published in arXiv (Cornell University) (Cornell University) · EMNLP2021 camera-ready
arxiv created 2021/11/18 · openalex publication_date 2021/11/18 · arxiv updated 2021/11/19 · openalex created_date 2021/11/22 · openalex updated_date 2026/08/08
Aspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources and reduce the error propagation in the pipeline. However, most of the existing joint models only focus on the benefits of encoder sharing between subtasks but ignore the difference. Therefore, we propose a joint ABSA model, which not only enjoys the benefits of encoder sharing but also focuses on the difference to improve the effectiveness of the model. In detail, we introduce a dual-encoder design, in which a pair encoder especially focuses on candidate aspect-opinion pair classification, and the original encoder keeps attention on sequence labeling. Empirical results show that our proposed model shows robustness and significantly outperforms the previous state-of-the-art on four benchmark datasets.