natural-language-processing-10

Unsupervised Extractive Summarization

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unsupervised-extractive-summarization-10

Trend

Dataset

Best Model

Actions

arXiv Summarization Dataset

Pubmed

FacetSum

Libraries

i

Use these libraries to find unsupervised-extractive-summarization-10 models and implementations

Datasets

Pubmed

arXiv Summarization Dataset

FacetSum

XWikiRef

Subtasks

No subtasks available.

Most implemented papers

A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

Franck Dernoncourt, Arman Cohan, Seokhwan Kim, Doo Soon Kim, Trung Bui, W. Chang, Nazli Goharian•Sat Mar 31 2018

This work proposes the first model for abstractive summarization of single, longer-form documents (e.g., research papers), consisting of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.

857

Content

FacetSum

0

Paper Graph

Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

A. Tixier, M. Vazirgiannis, Polykarpos Meladianos•Thu Aug 31 2017

A fully unsupervised, extractive text summarization system that leverages a submodularity framework that allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees is presented.

29 0

Paper Graph

Plain English Summarization of Contracts

Junyi Jessy Li, Laura Manor•Sat Jun 01 2019

The task of summarizing such legal documents in plain English, which would enable users to have a better understanding of the terms they are accepting, is proposed and a call for resource and technique development for simplification and style transfer for legal language is made.

58 0

Paper Graph

Sentence Centrality Revisited for Unsupervised Summarization

Mirella Lapata, Hao Zheng•Fri Jun 07 2019

An unsupervised approach arguing that it is unrealistic to expect large-scale and high-quality training data to be available or created for different types of summaries, domains, or languages is developed.

182 0

Paper Graph

Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers

Ming Zhou, Furu Wei, Shusheng Xu, Xingxing Zhang, Yi Wu•Thu Oct 15 2020

This work finds that transformer attentions can be used to rank sentences for unsupervised extractive summarization by first pre-train a hierarchical transformer model using unlabeled documents only and then proposing a method to rank sentence-level self-attentions and pre-training objectives.

45 0

Paper Graph

Unsupervised Abstractive Summarization of Bengali Text Documents

Radia Rayan Chowdhury, Mir Tafseer Nayeem, Tahsin Tasnim Mim, Md. Saifur Rahman Chowdhury, Taufiqul Jannat•Mon Jan 25 2021

This work proposes a graph-based unsupervised abstractive summarization system in the single-document setting for Bengali text documents, which requires only a Part-Of-Speech (POS) tagger and a pre-trained language model trained on Bengali texts.

30 0

Paper Graph

Unsupervised Extractive Summarization using Pointwise Mutual Information

He He, Vishakh Padmakumar•Wed Feb 10 2021

This work proposes new metrics of relevance and redundancy using pointwise mutual information (PMI) between sentences, which can be easily computed by a pre-trained language model and outperforms similarity-based methods on datasets in a range of domains.

49 0

Paper Graph

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Xingdi Yuan, Rui Meng, Tong Wang, Khushboo Thaker, Yue Dong, Lei Zhang, Daqing He•Sun May 30 2021

Faceted summarization will spur further advances in summarization research and foster the development of NLP systems that can leverage the structured information in both long texts and summaries, according to this study.

49 0

Paper Graph

Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering

R. A. Pugoy, Hung-Yu kao•Thu Dec 31 2020

This work pioneer the first extractive summarization-based collaborative filtering model called ESCOFILT and argues that its approach enhances both rating prediction accuracy and user/item explainability and proposes a comprehensive set of criteria that assesses the real-life explainability of explanations.

29 0

Paper Graph

Adding a benchmark result helps the community track progress.