natural-language-processing-11

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 extractive-summarization-11

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find extractive-summarization-11 models and implementations

HHousen/TransformerSum

2 papers 235

Datasets

SubSumE

Subtasks

No subtasks available.

Most implemented papers

Fine-tune BERT for Extractive Summarization

Yang Liu•Sun Mar 24 2019

BERTSUM, a simple variant of BERT, for extractive summarization, is described, which is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L.

520

Content

kedz/nnsum

2 papers 98

0

Paper Graph

Leveraging BERT for Extractive Text Summarization on Lectures

Derek Miller•Thu Jun 06 2019

This paper reports on the project called Lecture Summarization Service, a python based RESTful service that utilizes the BERT model for text embeddings and KMeans clustering to identify sentences closes to the centroid for summary selection.

266 0

Paper Graph

SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents

Ramesh Nallapati, Bowen Zhou, Feifei Zhai•Sun Nov 13 2016

SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art.

1312 0

Paper Graph

Generating Wikipedia by Summarizing Long Sequences

Noam Shazeer, Peter J. Liu, Lukasz Kaiser, Ryan Sepassi, Mohammad Saleh, Etienne Pot, Ben Goodrich•Mon Jan 29 2018

It is shown that generating English Wikipedia articles can be approached as a multi- document summarization of source documents and a neural abstractive model is introduced, which can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles.

851 0

Paper Graph

AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization

Asli Celikyilmaz, W. Bruce Croft, Rahul Jha, Keping Bi•Sun Apr 12 2020

Two adaptive learning models are presented: AREDSUM-SEQ that jointly considers salience and novelty during sentence selection; and a two-step AREDsUM-CTX that scores salience first, then learns to balancesalience and redundancy, enabling the measurement of the impact of each aspect.

23 0

Paper Graph

Diversity driven attention model for query-based abstractive summarization

Balaraman Ravindran, Mitesh M. Khapra, Preksha Nema, Anirban Laha•Tue Apr 25 2017

This work proposes a model for the query-based summarization task based on the encode-attend-decode paradigm with two key additions: a query attention model which learns to focus on different portions of the query at different time steps and a new diversity based Attention model which aims to alleviate the problem of repeating phrases in the summary.

173 0

Paper Graph

Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model

Suyi Li, Dragomir R. Radev, Alexander R. Fabbri, Irene Li, Tianwei She•Mon Jun 03 2019

This work introduces Multi-News, the first large-scale MDS news dataset, and proposes an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets.

665 0

Paper Graph

Extractive Summarization as Text Matching

Pengfei Liu, Xipeng Qiu, Ming Zhong, Xuanjing Huang, Danqing Wang, Yiran Chen•Sat Apr 18 2020

This paper forms the extractive summarization task as a semantic text matching problem, in which a source document and candidate summaries will be matched in a semantic space to create a semantic matching framework.

500 0

Paper Graph

Screenplay Summarization Using Latent Narrative Structure

Mirella Lapata, Pinelopi Papalampidi, Frank Keller, Lea Frermann•Sun Apr 26 2020

It is proposed to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models and formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays.

43 0

Paper Graph

Adding a benchmark result helps the community track progress.