ACL 2021long256 citations

BinaryBERT: Pushing the Limit of BERT Quantization

Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jin Jin, Xin Jiang, Qun Liu, Michael Lyu

Abstract

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks. Code will be released.

BibTeX
@inproceedings{bai-etal-2021-binarybert,
    title = "{B}inary{BERT}: Pushing the Limit of {BERT} Quantization",
    author = "Bai, Haoli  and
      Zhang, Wei  and
      Hou, Lu  and
      Shang, Lifeng  and
      Jin, Jin  and
      Jiang, Xin  and
      Liu, Qun  and
      Lyu, Michael  and
      King, Irwin",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.334/",
    doi = "10.18653/v1/2021.acl-long.334",
    pages = "4334--4348"
}
BinaryBERT: Pushing the Limit of BERT Quantization · ACL 2021