DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization

Zheng Li, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew O. Arnold, Bing Xiang, Dan Roth. DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 203-211, Association for Computational Linguistics, 2022. [doi]

Authors

Zheng Li

This author has not been identified. It may be one of the following persons: Look up 'Zheng Li' in Google

Zijian Wang

This author has not been identified. Look up 'Zijian Wang' in Google

Ming Tan

This author has not been identified. Look up 'Ming Tan' in Google

Ramesh Nallapati

This author has not been identified. Look up 'Ramesh Nallapati' in Google

Parminder Bhatia

This author has not been identified. Look up 'Parminder Bhatia' in Google

Andrew O. Arnold

This author has not been identified. Look up 'Andrew O. Arnold' in Google

Bing Xiang

This author has not been identified. Look up 'Bing Xiang' in Google

Dan Roth

This author has not been identified. Look up 'Dan Roth' in Google