Abstractive Multi-Document Summarization Based on Semantic Link Network

Li, Wei; Zhuge, Hai

doi:10.1109/tkde.2019.2922957

Cited by 39 publications

(25 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results demonstrate that our event extraction model is able to extract much more rich event information from news text, which is helpful for document summarization. Our event extraction results can also be used for abstractive document summarization [32].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Joint Event Extraction Based on Hierarchical Event Schemas From FrameNet

Cheng

Wang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Event extraction is useful for many practical applications, such as news summarization and information retrieval. However, the popular automatic context extraction (ACE) event extraction program only defines very limited and coarse event schemas, which may not be suitable for practical applications. FrameNet is a linguistic corpus that defines complete semantic frames and frame-to-frame relations. As frames in FrameNet share highly similar structures with event schemas in ACE and many frames actually express events, we propose to redefine the event schemas based on FrameNet. Specifically, we extract frames expressing event information from FrameNet and leverage the frame-to-frame relations to build a hierarchy of event schemas that are more fine-grained and have much wider coverage than ACE. Based on the new event schemas, we propose a joint event extraction approach that leverages the hierarchical structure of event schemas and frame-to-frame relations in FrameNet. The extensive experiments have verified the advantages of our hierarchical event schemas and the effectiveness of our event extraction model. We further apply the results of our event extraction model on news summarization. The results show that the summarization approach based on our event extraction model achieves significant better performance than several state-ofthe-art summarization approaches, which also demonstrates that the hierarchical event schemas and event extraction model are promising to be used in the practical applications.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Entity mentions are extracted based on dependency parsing tree. For further details of the entity mention extraction, see our previous work [32]. The valid candidate arguments are restricted as the extracted entity mentions.…”

Section: B Event Argument Extractionmentioning

confidence: 99%

Joint Event Extraction Based on Hierarchical Event Schemas From FrameNet

Cheng

Wang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Abstractive MDS approaches have met with limited success. Traditional approaches mainly include: sentence fusion-based (Banerjee et al, 2015;Filippova and Strube, 2008;Barzilay and McKeown, 2005;Barzilay, 2003), information extractionbased (Li, 2015;Pighin et al, 2014;Wang and Cardie, 2013;Genest and Lapalme, 2011;Li and Zhuge, 2019) and paraphrasing-based (Bing et al, 2015;Berg-Kirkpatrick et al, 2011;Cohn and Lapata, 2009). More recently, some researches parse the source text into AMR representation and then generate summary based on it (Liao et al, 2018).…”

Section: Abstractive Mdsmentioning

confidence: 99%

Leveraging Graph to Improve Abstractive Multi-Document Summarization

Li¹,

Xiao²,

Liu³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multidocument summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries. Furthermore, pre-trained language models can be easily combined with our model, which further improve the summarization performance significantly. Empirical results on the WikiSum and MultiNews dataset show that the proposed architecture brings substantial improvements over several strong baselines.

show abstract

“…Different from the traditional Semantic Net, SLN emphasizes on self-organized "link", on the basic self-organization operations of a complex system, on the emerging semantics [13], and on the automatic discovery of semantic links. The theory and method of SLN have been applied to various application areas, such as building and maintaining Peer-to-Peer networks [15,16], discovering and representing Knowledge Flow [17], supporting Cyber-Physical-Social Intelligence [18][19][20][21], and serving as a methodology for extractive or abstractive text summarization or even for multimedia summarization [1,7,10,[22][23][24]. Summarizing citations can be regarded as a kind of group-based extractive summarization, which can also generate coherent and readable summaries.…”

Section: Related Workmentioning

confidence: 99%

Grouping sentences as better language unit for extractive text summarization

Cao

Zhuge

2020

Future Generation Computer Systems

Self Cite

View full text Add to dashboard Cite

Most existing methods for extractive text summarization aim to extract important sentences with statistical or linguistic techniques and concatenate these sentences as a summary. However, the extracted sentences are usually incoherent. The problem becomes worse when the source text and the summary are long and based on logical reasoning. The motivation of this paper is to answer the following two related questions: What is the best language unit for constructing a summary that is coherent and understandable? How is the extractive summarization process based on the language unit? Extracting larger language units such as a group of sentences or a paragraph is a natural way to improve the readability of summary as it is rational to assume that the original sentences within a larger language unit are coherent. This paper proposes a framework for group-based text summarization that clusters semantically related sentences into groups based on Semantic Link Network (SLN) and then ranks the groups and concatenates the top-ranked ones into a summary. A two-layer SLN model is used to generate and rank groups with semantic links including the is-part-of link, sequential link, similar-to link, and cause-effect link. The experimental results show that summaries composed by group or paragraph tend to contain more key words or phrases than summaries composed by sentences; and, summaries composed by groups contain more key words or phrases than those composed by paragraphs, especially when the average length of source texts is from 7,000 words to 17,000 words, which is the usual length of scientific papers. Further, we compare seven clustering algorithms for generating groups and propose five strategies for generating groups with the four types of semantic links.

show abstract

Abstractive Multi-Document Summarization Based on Semantic Link Network

Cited by 39 publications

References 49 publications

Joint Event Extraction Based on Hierarchical Event Schemas From FrameNet

Joint Event Extraction Based on Hierarchical Event Schemas From FrameNet

Leveraging Graph to Improve Abstractive Multi-Document Summarization

Grouping sentences as better language unit for extractive text summarization

Contact Info

Product

Resources

About