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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization

文献类型：期刊论文

作者Zhao, Henghui1; Zhang, Wensheng1,2; Huang, Mengxing1; Feng, Siling1; Wu, Yuanyuan1
刊名ELECTRONICS
出版日期2023-05-10
卷号12期号:10页码:12
关键词graph neural network heterogeneous graph attention mechanism implicit topic
DOI10.3390/electronics12102184
通讯作者Zhang, Wensheng(wensheng.zhang@ia.ac.cn) ; Huang, Mengxing(huangmx09@hainanu.edu.cn)
英文摘要Extractive text summarization selects the most important sentences from a document, preserves their original meaning, and produces an objective and fact-based summary. It is faster and less computationally intensive than abstract summarization techniques. Learning cross-sentence relationships is crucial for extractive text summarization. However, most of the language models currently in use process text data sequentially, which makes it difficult to capture such inter-sentence relations, especially in long documents. This paper proposes an extractive summarization model based on the graph neural network (GNN) to address this problem. The model effectively represents cross-sentence relationships using a graph-structured document representation. In addition to sentence nodes, we introduce two nodes with different granularity in the graph structure, words and topics, which bring different levels of semantic information. The node representations are updated by the graph attention network (GAT). The final summary is obtained using the binary classification of the sentence nodes. Our text summarization method was demonstrated to be highly effective, as supported by the results of our experiments on the CNN/DM and NYT datasets. To be specific, our approach outperformed baseline models of the same type in terms of ROUGE scores on both datasets, indicating the potential of our proposed model for enhancing text summarization tasks.
资助项目National Natural Science Foundation of China[82260362] ; National Natural Science Foundation of China[62241202] ; National Key R&D Program of China[2021ZD0111000]
WOS研究方向Computer Science ; Engineering ; Physics
语种英语
出版者MDPI
WOS记录号WOS:000996247200001
资助机构National Natural Science Foundation of China ; National Key R&D Program of China
源URL[http://ir.ia.ac.cn/handle/173211/53384]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Zhang, Wensheng; Huang, Mengxing
作者单位1.Hainan Univ, Sch Informat & Commun Engn, Haikou 570100, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Henghui,Zhang, Wensheng,Huang, Mengxing,et al. A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization[J]. ELECTRONICS,2023,12(10):12.
APA Zhao, Henghui,Zhang, Wensheng,Huang, Mengxing,Feng, Siling,&Wu, Yuanyuan.(2023).A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization.ELECTRONICS,12(10),12.
MLA Zhao, Henghui,et al."A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization".ELECTRONICS 12.10(2023):12.

入库方式： OAI收割

来源：自动化研究所

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。