TY - GEN
T1 - Multiplex Graph Neural Network for Extractive Text Summarization
AU - Jing, Baoyu
AU - You, Zeyu
AU - Yang, Tao
AU - Fan, Wei
AU - Tong, Hanghang
N1 - Jing and Tong are partially supported by NSF (1947135 and 1939725).
PY - 2021
Y1 - 2021
N2 - Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have leveraged graph neural networks to capture the inter-sentential relationship (e.g., the discourse graph) to learn contextual sentence embedding. However, those approaches neither consider multiple types of inter-sentential relationships (e.g., semantic similarity & natural connection), nor model intra-sentential relationships (e.g, semantic & syntactic relationship among words). To address these problems, we propose a novel Multiplex Graph Convolutional Network (Multi-GCN) to jointly model different types of relationships among sentences and words. Based on Multi-GCN, we propose a Multiplex Graph Summarization (Multi-GraS) model for extractive text summarization. Finally, we evaluate the proposed models on the CNN/DailyMail benchmark dataset to demonstrate the effectiveness of our method.
AB - Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have leveraged graph neural networks to capture the inter-sentential relationship (e.g., the discourse graph) to learn contextual sentence embedding. However, those approaches neither consider multiple types of inter-sentential relationships (e.g., semantic similarity & natural connection), nor model intra-sentential relationships (e.g, semantic & syntactic relationship among words). To address these problems, we propose a novel Multiplex Graph Convolutional Network (Multi-GCN) to jointly model different types of relationships among sentences and words. Based on Multi-GCN, we propose a Multiplex Graph Summarization (Multi-GraS) model for extractive text summarization. Finally, we evaluate the proposed models on the CNN/DailyMail benchmark dataset to demonstrate the effectiveness of our method.
UR - http://www.scopus.com/inward/record.url?scp=85125130803&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125130803&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.emnlp-main.11
DO - 10.18653/v1/2021.emnlp-main.11
M3 - Conference contribution
AN - SCOPUS:85125130803
T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 133
EP - 139
BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -