Compressing large-scale transformer-based models: A case study on bert

Prakhar Ganesh, Yao Chen, Xin Lou, Mohammad Ali Khan, Yin Yang, Hassan Sajjad, Preslav Nakov, Deming Chen, Marianne Winslett

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)1061-1080
Number of pages20
JournalTransactions of the Association for Computational Linguistics
StatePublished - Sep 21 2021

ASJC Scopus subject areas

  • Communication
  • Human-Computer Interaction
  • Linguistics and Language
  • Computer Science Applications
  • Artificial Intelligence


Dive into the research topics of 'Compressing large-scale transformer-based models: A case study on bert'. Together they form a unique fingerprint.

Cite this