Transformer-Based Multi-aspect Modeling for Multi-aspect Multi-sentiment Analysis

摘要：

　　Aspect-based sentiment analysis(ABSA)aims at analyz-ing the sentiment of a given aspect in a sentence.Recently,neu-ral network-based methods have achieved promising results in existing ABSA datasets.However,these datasets tend to degenerate to sentence-level sentiment analysis because most sentences contain only one aspect or multiple aspects with the same sentiment polarity.To facilitate the research of ABSA,NLPCC 2020 Shared Task 2 releases a new large-scale Multi-Aspect Multi-Sentiment(MAMS)dataset.In the MAMS dataset,each sentence contains at least two different aspects with different senti-ment polarities,which makes ABSA more complex and challenging.To address the challenging dataset,we re-formalize ABSA as a problem of multi-aspect sentiment analysis,and propose a novel Transformer-based Multi-aspect Modeling scheme(TMM),which can capture potential rela-tions between multiple aspects and simultaneously detect the sentiment of all aspects in a sentence.Experiment results on the MAMS dataset show that our method achieves noticeable improvements compared with strong baselines such as BERT and RoBERTa,and finally ranks the 2nd in NLPCC 2020 Shared Task 2 Evaluation.

关键词： ABSA MAMS Neural network Transformer Multi-aspect Modeling

作者: Zhen Wu Chengcan Ying Xinyu Dai Shujian Huang Jiajun Chen

作者单位: National Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210023,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: 1397-1408

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）