Unsupervised Extractive Summarization

17 papers with code • 3 benchmarks • 4 datasets

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

Most implemented papers

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

acohan/long-summarization NAACL 2018

Neural abstractive summarization models have led to promising results in summarizing relatively short documents.

Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

Tixierae/EMNLP2017_NewSum WS 2017

We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research.

Plain English Summarization of Contracts

lauramanor/legal_summarization WS 2019

We propose 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.

Sentence Centrality Revisited for Unsupervised Summarization

mswellhao/PacSum ACL 2019

Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets.

Discourse-Aware Unsupervised Summarization of Long Scientific Documents

mirandrom/HipoRank 1 May 2020

We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.

Unsupervised Abstractive Summarization of Bengali Text Documents

tafseer-nayeem/BengaliSummarization EACL 2021

We also provide a human-annotated dataset with document-summary pairs to evaluate our abstractive model and to support the comparison of future abstractive summarization systems of the Bengali Language.

Unsupervised Extractive Summarization using Pointwise Mutual Information

vishakhpk/mi-unsup-summ EACL 2021

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document.

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

reinaldncku/escofilt ACL 2021

Our explainability study demonstrates the superiority of and preference for summary-level explanations over other explanation types.