Hierarchical Sequence Labeling Model for Aspect Sentiment Triplet Extraction

摘要：

　　Aspect sentiment triplet extraction is an emerging task in aspect-based sentiment analysis,which aims at simultaneously identify-ing the aspect,the opinion expression,and the sentiment from a given review sentence.Existing studies divide this task into many sub-tasks and process them in a pipeline manner,which ignores the relevance between different sub-tasks and leads to error accumulation.In this paper,we propose a hierarchical sequence labeling model(HSLM)to recognize the sentiment triplets in an end-to-end manner.Concretely,HSLM consists of an aspect-level sequence labeling module,an opinion-level sequence label-ing module,and a sentiment-level sequence labeling module.To learn the interactions between the above three modules,we further design three information fusion mechanisms,including aspect feature fusion mecha-nism,opinion feature fusion mechanism,and global feature fusion mecha-nism to refine high-level semantic information.To verify the effectiveness of our model,we conduct comprehensive experiments on four benchmark datasets.The experimental results demonstrate that our model achieves state-of-the-art performances.

关键词： Aspect sentiment triplet extraction Aspect-based sentiment analysis Hierarchical neural network

作者: Peng Chen Shaowei Chen Jie Liu

作者单位: College of Computer Science,Nankai University,Tianjin,China College of Artificial Intelligence,Nankai University,Tianjin,China

会议类型: 国际会议

会议名称: 9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)

会议地点: 郑州

会议语种:英文

页码: 654-666

在线出版日期: 2020-10-14（万方平台首次上网日期，不代表论文的发表时间）