自动化学报2025，Vol.51Issue(6)：1290-1304,15.DOI:10.16383/j.aas.c240541
基于双向多视角关系图卷积网络的论辩对抽取方法
Argument Pair Extraction Method Based on Bidirectional Multi-Perspective Relational Graph Convolutional Network
摘要
Abstract
Argument pair extraction,which aims to extract interactive argument pairs from two paragraphs of dia-logical documents,is an important research task in argument mining field.Existing research decomposes this task into sequence tagging and relation classification,extracting argument pairs by predicting sentence-level relation-ships between paragraphs.However,these studies lack in explicit modeling of overall argument-level semantics and fine-grained semantic logical information within sentences,and failure to adequately account for the complex con-text-aware interaction relationship between two paragraphs.Based on this we propose a bidirectional multi-per-spective relation graph convolutional network.Firstly,we construct argument relation graphs from intra-paragraph,dependency syntactic,and inter-paragraph perspectives,respectively,leveraging graph structures to better repres-ent the logical structure and semantic interaction relationships within the text,to enrich the model with rich con-textual semantic information.Then,by introducing multi-perspective relation graph convolutional module and graph matching module,achieve bidirectional interactions between two paragraphs,fully utilizing different levels of interaction between arguments to enhance the model's ability to capture semantic connections across paragraph-level arguments and improve the accuracy of argument relation recognition.Experimental results show that the method proposed in this paper significantly improves performance compared to baseline models.关键词
论辩对抽取/图卷积网络/论辩挖掘/多视角关系图Key words
Argument pair extraction/graph convolutional network/argument mining/multi-perspective relation graph引用本文复制引用
张虎,吴增泰,王宇杰..基于双向多视角关系图卷积网络的论辩对抽取方法[J].自动化学报,2025,51(6):1290-1304,15.基金项目
国家自然科学基金(62176145,62476161)资助Supported by National Natural Science Foundation of China(62176145,62476161) （62176145,62476161）
