natural-language-processing

Unsupervised Sentence Summarization

3260 papers • 126 benchmarks • 313 datasets

Generating a summary of a given sentence without supervision.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unsupervised-sentence-summarization

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find unsupervised-sentence-summarization models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction

Raphael Schumann, K. Markert, Lili Mou, Olga Vechtomova, Yao Lu•Sun May 03 2020

This work proposes a new state-of-the art for unsupervised sentence summarization according to ROUGE scores, and demonstrates that the commonly reported RouGE F1 metric is sensitive to summary length.

44

Content

0

Paper Graph

Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder

Raphael Schumann•Thu Sep 13 2018

An unsupervised approach to summarize sentences in abstractive way using Variational Autoencoder, showing that shorter sentences can not beat a simple baseline but yield higher ROUGE scores than trying to reconstruct the whole sentence.

21 0

Paper Graph

Simple Unsupervised Summarization by Contextual Matching

Jiawei Zhou, Alexander M. Rush•Sun Jun 30 2019

An unsupervised method for sentence summarization using only language modeling that employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain by using a product-of-experts criteria.

33 0

Paper Graph

Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization

Chenyang Huang, Lili Mou, Puyuan Liu•Fri May 27 2022

This work proposes a Non-Autoregressive Unsupervised Summarization (NAUS) approach, which does not require parallel data for training, and first performs edit-based search towards a heuristically defined score, and generates a summary as pseudo-groundtruth.

20 0

Paper Graph

Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization

Dongmin Hyun, Xiting Wang, Chanyoung Park, Xing Xie, Hwanjo Yu•Tue Dec 20 2022

An abstractive model based on reinforcement learning without ground-truth summaries is devised that substantially outperforms both abstractive and extractive models, yet frequently generating new words not contained in input texts.

9 0

Paper Graph

Adding a benchmark result helps the community track progress.