SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Zhao, Jinming; Liu, Ming; Gao, Longxiang; Jin, Yuan; Du, Lan; Zhao, He; Zhang, He; Haffari, Gholamreza

doi:10.1145/3397271.3401327

Cited by 42 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, salient sentences are selected from each cluster, taking into account cluster score, until the desired length of the summary. Monash-Summ (Ju et al, 2020)-The system, inspired by SummPip (Zhao et al, 2020), proposes an unsupervised approach that leveraging linguistic knowledge to construct sentence graph. The graph nodes, which represent sentences, are further clustered.…”

Section: Systems Overviewmentioning

confidence: 99%

Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm

Chandrasekaran¹,

Feigenblat²,

Hovy³

et al. 2020

Proceedings of the First Workshop on Scholarly Document Processing

View full text Add to dashboard Cite

We present the results of three Shared Tasks held at the Scholarly Document Processing Workshop at EMNLP2020: CL-SciSumm, LaySumm and LongSumm. We report on each of the tasks, which received 18 submissions in total, with some submissions addressing two or three of the tasks. In summary, the quality and quantity of the submissions show that there is ample interest in scholarly document summarization, and the state of the art in this domain is at a midway point between being an impossible task and one that is fully resolved.

show abstract

Section: Systems Overviewmentioning

confidence: 99%

Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm

Chandrasekaran¹,

Feigenblat²,

Hovy³

et al. 2020

Proceedings of the First Workshop on Scholarly Document Processing

View full text Add to dashboard Cite

show abstract

“…We adopt the SummPip (Zhao et al, 2020) as our baseline model, and we modify the pipeline architecture for summarizing scholarly documents. Two new steps are introduce for adapting scientific domain, one is to remove irrelevant sentences and the other is to control the length of generated summary.…”

Section: System Overviewmentioning

confidence: 99%

“…We construct the sentence graph, where each node represents a sentence, and nodes are connected if they meet the linguistic requirements. To identify this structure, we borrow the components from the previous work (Zhao et al, 2020). Specifically, this pipeline consists of discovering deverbal noun reference, finding the same entity continuation, recognizing discourse markers, and calculating sentence similarity by taking the cosine similarity.…”

Section: Graph Constructionmentioning

confidence: 99%

See 1 more Smart Citation

Monash-Summ@LongSumm 20 SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline

Ju¹,

Liu

Gao

et al. 2020

Proceedings of the First Workshop on Scholarly Document Processing

Self Cite

View full text Add to dashboard Cite

The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task. It contains three shared tasks and we participate in the LongSumm shared task. In this paper, we describe our text summarization system, SciSummPip, inspired by SummPip (Zhao et al., 2020) that is an unsupervised text summarization system for multi-document in news domain. Our SciSummPip includes a transformer-based language model SciBERT (Beltagy et al., 2019) for contextual sentence representation, content selection with PageRank (Page et al., 1999), sentence graph construction with both deep and linguistic information, sentence graph clustering and withingraph summary generation. Our work differs from previous method in that content selection and a summary length constraint is applied to adapt to the scientific domain. The experiment results on both training dataset and blind test dataset show the effectiveness of our method, and we empirically verify the robustness of modules used in SciSummPip with BERTScore (Zhang et al., 2019a).

show abstract

“…In Monash-Summ (Ju et al, 2020), they propose an unsupervised approach that leverages linguistic knowledge to construct a sentence graph like in SummPip (Zhao et al, 2020). The graph nodes, which represent sentences, are further clustered to control the summary length, while the final abstractive summary is created from the key phrases and discourse from each cluster.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised document summarization using pre-trained sentence embeddings and graph centrality

Juan¹,

Milios²

2021

Proceedings of the Second Workshop on Scholarly Document Processing

View full text Add to dashboard Cite

This paper describes our submission for the LongSumm task in SDP 2021. We propose a method for incorporating sentence embeddings produced by deep language models into extractive summarization techniques based on graph centrality in an unsupervised manner. The proposed method is simple, fast, can summarize any document of any size and can satisfy any length constraints for the summaries produced. The method offers competitive performance to more sophisticated supervised methods and can serve as a proxy for abstractive summarization techniques.

show abstract

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Cited by 42 publications

References 7 publications

Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm

Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm

Monash-Summ@LongSumm 20 SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline

Unsupervised document summarization using pre-trained sentence embeddings and graph centrality

Contact Info

Product

Resources

About