Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation Bowen Wu author Huan Zhang author MengYuan Li author Zongsheng Wang author Qihang Feng author Junhong Huang author Baoxun Wang author 2020-12 text Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing Kam-Fai Wong editor Kevin Knight editor Hua Wu editor Association for Computational Linguistics Suzhou, China conference publication wu-etal-2020-towards 10.18653/v1/2020.aacl-main.9 https://aclanthology.org/2020.aacl-main.9/ 2020-12 70 79