Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 16, 2025InformationOpen Access

Efficient Transformer-Based Abstractive Urdu Text Summarization Through Selective Attention Pruning

View Full Paper
Ask AI
Bookmark
Share

Authors

MAMuhammad AzharAAAdeen AmjadGFGhulam Farid

Discussion

Loading...

Member takes

Overview

Innovative pruning reduces computational complexity in Urdu text summarization, suggesting enhanced natural language processing outcomes.

Key Points

  • Abstractive summarization improves with efficient transformer models, focusing on Urdu texts.
  • Key metrics indicate enhanced performance in natural language processing comparisons with original models.
  • Efficient model optimization involves selective removal of attention heads to boost accuracy.
  • These findings support broader applications in low-resource language processing and efficiency.

Cite This Study

Azhar et al. (2025) studied this question.

synapsesocial.com/papers/6925198ec0ce034ddc353472https://doi.org/10.3390/info16110991
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. 1Evaluating Classical and Transformer-Based Models for Urdu Abstractive Text Summarization: A Systematic Review2025 · 4 citations
  2. 2Bidirectional and Auto-Regressive Transformer (BART) for Indonesian Abstractive Text Summarization2024 · 9 citations
  3. 3Enhanced extractive text summarization framework for low-resourced Urdu language2026
  4. 4Low Resource Summarization using Pre-trained Language Models2024 · 21 citations
  5. 5Beyond Extractive Methods – Navigating the landscape of Abstractive Summarization Methods2024