A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization
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 cru...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/10/2184 |
| _version_ | 1797600357573984256 |
|---|---|
| author | Henghui Zhao Wensheng Zhang Mengxing Huang Siling Feng Yuanyuan Wu |
| author_facet | Henghui Zhao Wensheng Zhang Mengxing Huang Siling Feng Yuanyuan Wu |
| author_sort | Henghui Zhao |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T03:48:00Z |
| format | Article |
| id | doaj.art-af4ed9e3241e40cb871871405e595f4a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T03:48:00Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-af4ed9e3241e40cb871871405e595f4a2023-11-18T01:08:54ZengMDPI AGElectronics2079-92922023-05-011210218410.3390/electronics12102184A Multi-Granularity Heterogeneous Graph for Extractive Text SummarizationHenghui Zhao0Wensheng Zhang1Mengxing Huang2Siling Feng3Yuanyuan Wu4School of Information and Communication Engineering, Hainan University, Haikou 570100, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570100, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570100, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570100, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570100, ChinaExtractive 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.https://www.mdpi.com/2079-9292/12/10/2184graph neural networkheterogeneous graphattention mechanismimplicit topic |
| spellingShingle | Henghui Zhao Wensheng Zhang Mengxing Huang Siling Feng Yuanyuan Wu A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization Electronics graph neural network heterogeneous graph attention mechanism implicit topic |
| title | A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization |
| title_full | A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization |
| title_fullStr | A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization |
| title_full_unstemmed | A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization |
| title_short | A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization |
| title_sort | multi granularity heterogeneous graph for extractive text summarization |
| topic | graph neural network heterogeneous graph attention mechanism implicit topic |
| url | https://www.mdpi.com/2079-9292/12/10/2184 |
| work_keys_str_mv | AT henghuizhao amultigranularityheterogeneousgraphforextractivetextsummarization AT wenshengzhang amultigranularityheterogeneousgraphforextractivetextsummarization AT mengxinghuang amultigranularityheterogeneousgraphforextractivetextsummarization AT silingfeng amultigranularityheterogeneousgraphforextractivetextsummarization AT yuanyuanwu amultigranularityheterogeneousgraphforextractivetextsummarization AT henghuizhao multigranularityheterogeneousgraphforextractivetextsummarization AT wenshengzhang multigranularityheterogeneousgraphforextractivetextsummarization AT mengxinghuang multigranularityheterogeneousgraphforextractivetextsummarization AT silingfeng multigranularityheterogeneousgraphforextractivetextsummarization AT yuanyuanwu multigranularityheterogeneousgraphforextractivetextsummarization |