A Spectral Method for Unsupervised Multi-Document Summarization

Wang, Kexiang; Chang, Baobao; Sui, Zhifang

doi:10.18653/v1/2020.emnlp-main.32

Cited by 12 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al (2019a) improve the model by encoding articles and summaries in the same space. Other novel approaches include using sentence compression in the seq2seq framework (Baziotis et al, 2019), jointly learning sentence fusion and paraphrasing (Nayeem et al, 2018), using graph neural networks to help extraction (Wang et al, 2020b), using spectral methods (Wang et al, 2020c), using transfer learning based on a novel pretraining method called gap-sentence prediction (Zhang et al, 2020a) on a news-specific corpus, among a few others Gu et al, 2020;.…”

Section: Related Workmentioning

confidence: 99%

AgreeSum: Agreement-Oriented Multi-Document Summarization

Pang¹,

Lelkes²,

Trần³

et al. 2021

Preprint

View full text Add to dashboard Cite

We aim to renew interest in a particular multidocument summarization (MDS) task which we call AgreeSum: agreement-oriented multidocument summarization. Given a cluster of articles, the goal is to provide abstractive summaries that represent information common and faithful to all input articles. Given the lack of existing datasets, we create a dataset for AgreeSum, and provide annotations on article-summary entailment relations for a subset of the clusters in the dataset. We aim to create strong baselines for the task by applying the top-performing pretrained singledocument summarization model PEGASUS onto AgreeSum, leveraging both annotated clusters by supervised losses, and unannotated clusters by T5-based entailment-related and language-related losses. Compared to other baselines, both automatic evaluation and human evaluation show better article-summary and cluster-summary entailment in generated summaries. On a separate note, we hope that our article-summary entailment annotations contribute to the community's effort in improving abstractive summarization faithfulness.

show abstract

Section: Related Workmentioning

confidence: 99%

AgreeSum: Agreement-Oriented Multi-Document Summarization

Pang¹,

Lelkes²,

Trần³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Quadratic multiple regression model and spectral relaxation approach for carreau nanofluid inclined magnetized dipole along stagnation point geometry

Din

Darvesh

Ayub

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Researchers across the world have tried to explore the impact of non-Newtonian liquid flowing via an extendable surface with the inclusion of various effects due to its industrial and engineering applications like polymer production, paper production, filament extrusion from a dye, etc. This study investigates the behavior of stagnation point flow of Carreau liquid attached with inclined magnetic effect and spectral relaxation approach is utilized here for the numerical outcome. In this study, a few other vital features are attached like the quadratic multiple regression model for Nusselt number evaluation, passive control of nanoparticles, viscus heating thermophoresis, Brownian motion, and mixed convection, etc. Velocity disbursement visibility is analyzed by placing an inclined magnetic field. Physical model generates collection of partial differential equations (PDEs) and these PDEs are moved into ordinary differential equations by a similarity transformations scheme. Further for numerical process, spectral relaxation method is used. Growth in K causes a reduction in velocity because this parameter K creates the impedance to flowing resulting in confines the movement of liquid in restricted the plate. Direct relation is found between $$Ec$$ Ec and the energy file. In the case of S > 1, physically it is a representation of Joule and viscous dissipations. This article is novel in its sense that the influence of oblique magnetic force and second order velocity slippage on Carreau nano liquid and its numerical computation with help of the spectral relaxation method has never been done before. Furthermore, the quadratic multiple regression model has been employed to find the heat transition rate in the status of the Nusselt number.

show abstract

Mining Both Commonality and Specificity From Multiple Documents for Multi-Document Summarization

2024

IEEE Access

View full text Add to dashboard Cite

The multi-document summarization task requires the designed summarizer to generate a short text that covers the important information of original multiple documents and satisfies content diversity. To fulfill the dual requirements of coverage and diversity in multi-document summarization, this study introduces a novel method. Initially, a class tree is constructed through hierarchical clustering of documents. Subsequently, a sentence selection method based on class tree is proposed for generating a summary. Specifically, a top-down traversal is performed on the class tree, during which sentences are selected from each node based on their similarity to the centroid of the documents within the node and their dissimilarity to the centroid of documents not belonging to the node. Sentences selected from the root node reflect the commonality of all document, and sentences selected from the sub nodes reflect the distinct specificity of the respective subclasses. Experimental results on standard text summarization datasets DUC '2002, DUC'2003, and DUC'2004 demonstrate that our proposed method significantly outperforms the variant method that considers only commonality of all documents, achieving average improvements of up to 1.54 and 1.42 in ROUGE-1 and ROUGE-L scores, respectively. Additionally, our method demonstrates significant superiority over another variant method that considers only the specificity of subclasses, achieving average improvements of up to 2.16 and 2.01 in Rouge-1 and ROUGE-L scores, respectively. Furthermore, extensive experiments on DUC'2004 and Multi-News datasets show that our method outperforms lots of competitive supervised and unsupervised multi-document summarization methods and yields considerable results.INDEX TERMS Class tree, commonality and specificity, hierarchical clustering of documents, multidocument summarization, pre-trained embedding representation.

show abstract

A Spectral Method for Unsupervised Multi-Document Summarization

Cited by 12 publications

References 34 publications

AgreeSum: Agreement-Oriented Multi-Document Summarization

AgreeSum: Agreement-Oriented Multi-Document Summarization

Quadratic multiple regression model and spectral relaxation approach for carreau nanofluid inclined magnetized dipole along stagnation point geometry

Mining Both Commonality and Specificity From Multiple Documents for Multi-Document Summarization

Contact Info

Product

Resources

About