Manara - Qatar Research Repository
tacl_a_00413.pdf (872.19 kB)

Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

Download (872.19 kB)
journal contribution
submitted on 2024-04-29, 10:03 and posted on 2024-04-29, 10:03 authored by Prakhar Ganesh, Yao Chen, Xin Lou, Mohammad Ali Khan, Yin Yang, Hassan Sajjad, Preslav Nakov, Deming Chen, Marianne Winslett

Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and computation-intensive to suit low- capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted considerable research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.

Other Information

Published in: Transactions of the Association for Computational Linguistics
See article on publisher's website:



  • English


MIT Press

Publication Year

  • 2021

License statement

This Item is licensed under the Creative Commons Attribution 4.0 International License.

Institution affiliated with

  • Hamad Bin Khalifa University
  • College of Science and Engineering - HBKU
  • Qatar Computing Research Institute - HBKU