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


Anthology ID:
2021.findings-acl.363
Volume:
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4147–4157
Language:
URL:
https://aclanthology.org/2021.findings-acl.363
DOI:
10.18653/v1/2021.findings-acl.363
Bibkey:
Cite (ACL):
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, and Niranjan Balasubramanian. 2021. On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4147–4157, Online. Association for Computational Linguistics.
Cite (Informal):
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (Ji et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-acl.363.pdf
Optional supplementary material:
 2021.findings-acl.363.OptionalSupplementaryMaterial.zip
Data
SQuADSST