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
A mutually enhanced multi-scale relation-aware graph convolutional network for argument pair extraction

文献类型：期刊论文

作者Zhu, Xiaofei5; Liu, Yidan5; Chen, Zhuo5; Chen, Xu4; Guo, Jiafeng3; Dietze, Stefan1,2
刊名JOURNAL OF INTELLIGENT INFORMATION SYSTEMS
出版日期2023-11-30
页码20
关键词Argument mining Argument pair extraction Transformer Graph convolutional network
ISSN号0925-9902
DOI10.1007/s10844-023-00826-9
英文摘要Argument pair extraction (APE) is a fine-grained task of argument mining which aims to identify arguments offered by different participants in some discourse and detect interaction relationships between arguments from different participants. In recent years, many research efforts have been devoted to dealing with APE in a multi-task learning framework. Although these approaches have achieved encouraging results, they still face several challenging issues. First, different types of sentence relationships as well as different levels of information exchange among sentences are largely ignored. Second, they solely model interactions between argument pairs either in an explicit or implicit strategy, while neglecting the complementary effect of the two strategies. In this paper, we propose a novel Mutually Enhanced Multi-Scale Relation-Aware Graph Convolutional Network (MMR-GCN) for APE. Specifically, we first design a multi-scale relation-aware graph aggregation module to explicitly model the complex relationships between review and rebuttal passage sentences. In addition, we propose a mutually enhancement transformer module to implicitly and interactively enhance representations of review and rebuttal passage sentences. We experimentally validate MMR-GCN by comparing with the state-of-the-art APE methods. Experimental results show that it considerably outperforms all baseline methods, and the relative performance improvement of MMR-GCN over the best performing baseline MRC-APE in terms of F1 score reaches to 3.48% and 4.43% on the two benchmark datasets, respectively.
资助项目National Natural Science Foundation of China ; Natural Science Foundation of Chongqing, China[CSTB2022NSCQ-MSX1672] ; Major Project of Science and Technology Research Program of Chongqing Education Commission of China[KJZD-M202201102] ; Federal Ministry of Education and Research[01IS21086] ; [62141201]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001109135000001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/38075]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Chen, Xu
作者单位1.Heinrich Heine Univ Dusseldorf, Inst Comp Sci, D-40225 Dusseldorf, Germany
2.Leibniz Inst Social Sci, Knowledge Technol Social Sci, D-50667 Cologne, Germany
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Chongqing Univ Technol, Coll Accounting, Chongqing 400054, Peoples R China
5.Chongqing Univ Technol, Coll Comp Sci & Engn, Chongqing 400054, Peoples R China
推荐引用方式
GB/T 7714		 Zhu, Xiaofei,Liu, Yidan,Chen, Zhuo,et al. A mutually enhanced multi-scale relation-aware graph convolutional network for argument pair extraction[J]. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS,2023:20.
APA Zhu, Xiaofei,Liu, Yidan,Chen, Zhuo,Chen, Xu,Guo, Jiafeng,&Dietze, Stefan.(2023).A mutually enhanced multi-scale relation-aware graph convolutional network for argument pair extraction.JOURNAL OF INTELLIGENT INFORMATION SYSTEMS,20.
MLA Zhu, Xiaofei,et al."A mutually enhanced multi-scale relation-aware graph convolutional network for argument pair extraction".JOURNAL OF INTELLIGENT INFORMATION SYSTEMS (2023):20.

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。