Extractive Text Summarization
32 papers with code • 5 benchmarks • 5 datasets
Given a document, selecting a subset of the words or sentences which best represents a summary of the document.
Benchmarks
These leaderboards are used to track progress in Extractive Text Summarization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Extractive Text Summarization models and implementations
CNN/Daily Mail
GovReport
DUC 2004
DebateSum
Most implemented papers
DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization.
Neural Extractive Text Summarization with Syntactic Compression
jiacheng-xu/neu-compression-sum
•
•
IJCNLP 2019
In this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression.
STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings
Our method creates an extractive summary by selecting the sentences with the closest embeddings to the document embedding.
Discourse-Aware Neural Extractive Text Summarization
jiacheng-xu/DiscoBERT
•
•
ACL 2020
Recently BERT has been adopted for document encoding in state-of-the-art text summarization models.
Reading Like HER: Human Reading Inspired Extractive Summarization
In this work, we re-examine the problem of extractive text summarization for long documents.
Extractive Multi-document Summarization using K-means, Centroid-based Method, MMR, and Sentence Position
Multi-document summarization is more challenging than single-document summarization since it has to solve the problem of overlapping information among sentences from different documents.
Heterogeneous Graph Neural Networks for Extractive Document Summarization
brxx122/HeterSUMGraph
•
•
ACL 2020
An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships.
Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
xssstory/STAS
•
•
Findings of the Association for Computational Linguistics 2020
We also find in experiments that our model is less dependent on sentence positions.
MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes
nianlonggu/memsum
•
•
ACL 2022
We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history.
Align and Attend: Multimodal Summarization with Dual Contrastive Losses
The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries.
