Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.8K
2.8K
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

3.0K
3.0K
Master Transcription Regulators02:23

Master Transcription Regulators

2.4K
2.4K
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

564
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
564
Alternative RNA Splicing02:18

Alternative RNA Splicing

4.0K
4.0K
Trimmed Mean01:10

Trimmed Mean

3.0K
While measuring the mean of a data set, care needs to be taken when associating the mean to its central tendency. The same goes for the arithmetic mean, the geometric mean, or the harmonic mean. This is because the presence of a single outlier data value can significantly affect the mean. That is, the mean is sensitive to fluctuations in the data set.
Although certain measures of central tendency are not sensitive to outliers, there are alternative versions of the mean that get around the...
3.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Occupational hazard awareness and safety-related knowledge among EMS students: evidence of a potential gap.

Scientific reports·2026
Same author

Corrigendum to "LLM predicts human behavior: A BERT-based approach for conscientiousness personality trait detection from online content" [Acta Psychologica 266 (2026), 106832].

Acta psychologica·2026
Same author

Evaluation of Video-Based Instruction and a 360° Virtual Reality Module on Personal Protective Equipment Competency and Infection Prevention in Healthcare Settings: A Quasi-Experimental Study.

Healthcare (Basel, Switzerland)·2026
Same author

Immune and non-immune hydrops fetalis in a Saudi tertiary center: etiologies, antenatal predictors, perinatal outcomes, and one-year survival in a seven-year cohort.

Frontiers in pediatrics·2026
Same author

LLM predicts human behavior: A BERT-based approach for conscientiousness personality trait detection from online content.

Acta psychologica·2026
Same author

Low muscle mass in interstitial lung disease: a systematic review and meta-analysis of prevalence and clinical associations.

BMC pulmonary medicine·2026

Related Experiment Video

Updated: Oct 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

Abstractive Arabic Text Summarization Based on Deep Learning.

Y M Wazery1, Marwa E Saleh1, Abdullah Alharbi2

  • 1Faculty of Computers and Information, Minia University, Minia, Egypt.

Computational Intelligence and Neuroscience
|January 24, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces an advanced abstractive Arabic text summarization system using a sequence-to-sequence model. The research found that Bidirectional Long Short-Term Memory networks with three layers achieve the best performance, outperforming previous studies.

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K

Related Experiment Videos

Last Updated: Oct 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K

Area of Science:

  • Natural Language Processing (NLP)
  • Artificial Intelligence (AI)
  • Deep Learning

Background:

  • Text summarization is a challenging NLP task, with abstractive summarization being less explored, especially for complex languages like Arabic.
  • Existing research often focuses on extractive methods, leaving a gap in abstractive Arabic summarization techniques.

Purpose of the Study:

  • To propose and evaluate an abstractive Arabic text summarization system based on a sequence-to-sequence model.
  • To investigate the performance of different deep artificial neural networks (GRU, LSTM, BiLSTM) within the sequence-to-sequence framework.
  • To compare word embedding models (skip-gram vs. CBOW) and attention mechanisms for Arabic text summarization.

Main Methods:

  • Developed a sequence-to-sequence model with encoder-decoder architecture using GRU, LSTM, and BiLSTM layers.
  • Implemented a global attention mechanism for improved summarization performance.
  • Utilized AraBERT preprocessing for better Arabic word understanding and employed skip-gram and CBOW word2Vec for word embeddings.
  • Built and ran models using the Keras library on Google Colab.

Main Results:

  • The proposed abstractive Arabic text summarization system achieved state-of-the-art results.
  • A three-layer Bidirectional Long Short-Term Memory (BiLSTM) encoder demonstrated superior performance compared to other configurations.
  • Abstractive summarization models using the skip-gram word2Vec model outperformed those using the CBOW word2Vec model.

Conclusions:

  • The developed abstractive Arabic text summarization system, particularly with a three-layer BiLSTM encoder and skip-gram word embeddings, represents a significant advancement in the field.
  • The study confirms the effectiveness of deep learning models and attention mechanisms for complex NLP tasks like Arabic text summarization.
  • This research provides a strong foundation for future work in low-resource language summarization.