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
Latest papers
Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model
Outcomes validate that our proposed model shows greatly enhanced performance as compared to the existent unsupervised state-of-the-art approaches.
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.
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.
CX DB8: A queryable extractive summarizer and semantic search engine
Competitive Debate's increasingly technical nature has left competitors looking for tools to accelerate evidence production.
DebateSum: A large-scale argument mining and summarization dataset
Finally, we present a search engine for this dataset which is utilized extensively by members of the National Speech and Debate Association today.
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.
Screenplay Summarization Using Latent Narrative Structure
Most general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront.
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.
Extractive Summarization as Text Matching
maszhongming/MatchSum
•
•
ACL 2020
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
nakhunchumpolsathien/ThaiSum
•
•
EACL 2021
Redundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step.
