Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 25, 2025Open Access

Evaluating Classical and Transformer-Based Models for Urdu Abstractive Text Summarization: A Systematic Review

View Full Paper
Ask AI
Bookmark
Share

Authors

MAMuhammad AzharAAAdeen AmjadDDDeshinta Arrova Dewi

Discussion

Loading...

Member takes

Overview

Systematic review demonstrates transformer-based models improve abstractive summarization in Urdu, highlighting mT5's efficiency.

Key Points

  • Transformer-based models significantly improve urdu abstractive summarization performance.
  • mT5 achieves a 0.42% average improvement in F1-score over the best baseline.
  • Using various datasets, mT5 outperforms Seq2Seq methods by 20% in ROUGE-L.
  • The study offers practical training strategies for effective low-resource language applications.

Cite This Study

Azhar et al. (2025) studied this question.

synapsesocial.com/papers/689a0933e6551bb0af8ce360https://doi.org/10.20944/preprints202507.1846.v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Efficient Transformer-Based Abstractive Urdu Text Summarization Through Selective Attention Pruning2025
  2. 2Enhanced extractive text summarization framework for low-resourced Urdu language2026
  3. 3Low Resource Summarization using Pre-trained Language Models2024 · 21 citations
  4. 4Abstractive Summarization for Urdu Video Description Generation2025
  5. 5A transformer-based Urdu image caption generation2024 · 2 citations