On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers

Ji, Tianchu; Jain, Shraddhan; Ferdman, Michael; Milder, Peter; Schwartz, H. Andrew; Balasubramanian, Niranjan

by Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian

Reference:

On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian, In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Association for Computational Linguistics, 2021.

Bibtex Entry:

@inproceedings{ferdman-acl-findings-inference-time-quantization-of-attention-values-in-transformers,
    title = "On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers",
    author = "Ji, Tianchu  and
      Jain, Shraddhan  and
      Ferdman, Michael  and
      Milder, Peter  and
      Schwartz, H. Andrew  and
      Balasubramanian, Niranjan",
    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
    month = aug,
    year = "2021",
  pdf={http://compas.cs.stonybrook.edu/%7Emferdman/downloads.php/ACL21-FINDINGS_On_the_Distribution_Sparsity,_and_Inference-time_Quantization_ofAttention_Values_in_Transformers.pdf},
    address = "Online",
    publisher = "Association for Computational Linguistics",
    pages = "4147--4157",
}