Dialogue Summarization with Static-Dynamic Structure Fusion Graph

Gao, Shen; Cheng, Xiuzhen; Li, Mingzhe; Chen, Xiuying; Li, Jinpeng; Zhao, Dongyan; Yan, Rui

doi:10.18653/v1/2023.acl-long.775

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative method, called the 'Abstractive' approach, generates summaries based on the core idea within the text. Both of them have made great progress within conventional summarization domains, such as news summarization and dialogue summarization Liu, Jia, and Zhu 2022;Dixit, Wang, and Chen 2023;Li et al 2023;Gao et al 2023).…”

Section: Introductionmentioning

confidence: 99%

MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships

Zhao,

He,

et al. 2024

AAAI

View full text Add to dashboard Cite

Social summarization aims to provide summaries for a large number of social texts (called posts) about a single topic. To extract a summary, both the representation of post and summary selection method are crucial. Previous methods introduce social relation to enhance post embedding to mitigate the sparse representation due to its brief and informal expression. However, they ignore that there are multiple relations between posts. Besides, existing graph-based centrality calculation approaches tend to select posts from one aspect. This leads to facet bias especially when there are multiple viewpoints. In this paper, we propose a model named MultiSum to improve social summarization. Specifically, 1) We use graph convolutional networks to fuse text content with social and semantic relations to improve post representation; 2) The similarity between the summary and all aspects is incorporated into the centrality score during the selection phase, encouraging the model to pay attention to different facets. Experimental results on English and Chinese corpora support the effectiveness of this model. Furthermore, external evaluations by human experts and large language models demonstrate the validity of MultiSum in facet coverage and redundancy reduction.

show abstract

Section: Introductionmentioning

confidence: 99%