中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Exploring rich structure information for aspect-based sentiment classification

文献类型：期刊论文

作者Zhu, Ling4; Zhu, Xiaofei4; Guo, Jiafeng1; Dietze, Stefan2,3
刊名JOURNAL OF INTELLIGENT INFORMATION SYSTEMS
出版日期2022-07-30
页码21
关键词Aspect-based sentiment classification Graph convolutional networks Attention mechanism Sentiment analysis
ISSN号0925-9902
DOI10.1007/s10844-022-00729-1
英文摘要Graph Convolutional Network (GCN) for aspect-based sentiment classification has attracted a lot of attention recently due to their promising performance in handling complex structure information. However, previous methods based on GCN focused mainly on examining the structure of syntactic dependency relationships, which were subject to the noise and sparsity problem. Furthermore, these methods tend to focus on one kind of structural information (namely syntactic dependency) while ignoring many other kinds of rich structures between words. To tackle these problems, we propose a novel GCN based model, named Structure-Enhanced Dual-Channel Graph Convolutional Network (SEDC-GCN). Specifically, we first exploit the rich structure information by constructing a text sequence graph and an enhanced dependency graph, then design a dual-channel graph encoder to model the structure information from the two graphs. After that, we propose two kinds of aspect-specific attention, i.e., aspect-specific semantic attention and aspect-specific structure attention, to learn sentence representation from two different perspectives, i.e., the semantic perspective based on the text encoder, and the structure perspective based on the dual-channel graph encoder. Finally, we merge the sentence representations from the above two perspectives and obtain the final sentence representation. We experimentally validate our proposed model SEDC-GCN by comparing with seven strong baseline methods. In terms of the metric accuracy, SEDC-GCN achieves performance gains of 74.42%, 77.74%, 83.30%, 81.73% and 90.75% on TWITTER, LAPTOP, REST14, REST15, and REST16, respectively, which are 0.35%, 4.22%, 1.62%, 0.70% and 2.01% better than the best performing baseline BiGCN. Similar performance improvements are also observed in terms of the metric macro-averaged F1 score. The ablation study further demonstrates the effectiveness of each component of SEDC-GCN.
资助项目National Natural Science Foundation of China[62141201] ; Federal Ministry of Education and Research[01IS21086]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000833443000001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/19490]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhu, Xiaofei
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Leibniz Inst Social Sci, Knowledge Technol Social Sci, D-50667 Cologne, Germany
3.Heinrich Heine Univ Dusseldorf, Inst Comp Sci, D-40225 Dusseldorf, Germany
4.Chongqing Univ Technol, Coll Comp Sci & Engn, Chongqing 400054, Peoples R China
推荐引用方式
GB/T 7714		 Zhu, Ling,Zhu, Xiaofei,Guo, Jiafeng,et al. Exploring rich structure information for aspect-based sentiment classification[J]. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS,2022:21.
APA Zhu, Ling,Zhu, Xiaofei,Guo, Jiafeng,&Dietze, Stefan.(2022).Exploring rich structure information for aspect-based sentiment classification.JOURNAL OF INTELLIGENT INFORMATION SYSTEMS,21.
MLA Zhu, Ling,et al."Exploring rich structure information for aspect-based sentiment classification".JOURNAL OF INTELLIGENT INFORMATION SYSTEMS (2022):21.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。