TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference

Deming Ye, Yankai Lin, Yufei Huang, Maosong Sun. TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference. In Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tür, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty 0002, Yichao Zhou, editors, Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021. pages 5798-5809, Association for Computational Linguistics, 2021. [doi]

Authors

Deming Ye

This author has not been identified. Look up 'Deming Ye' in Google

Yankai Lin

This author has not been identified. Look up 'Yankai Lin' in Google

Yufei Huang

This author has not been identified. Look up 'Yufei Huang' in Google

Maosong Sun

This author has not been identified. Look up 'Maosong Sun' in Google