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

doi:10.1162/tacl_a_00413

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

2021-09-21

68

OA

AI

DOI：10.1162/tacl_a_00413

Original

Original request for help

Save

Abstract

En 中文

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 resourcehungry and computation-intensive to suit lowcapability 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.

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

Abstract

Journal

Organization