Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning

Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning Chong Li author Shaonan Wang author Yunhao Zhang author Jiajun Zhang author Chengqing Zong author 2023-12 text Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing Houda Bouamor editor Juan Pino editor Kalika Bali editor Association for Computational Linguistics Singapore conference publication li-etal-2023-interpreting 10.18653/v1/2023.emnlp-main.1026 https://aclanthology.org/2023.emnlp-main.1026/ 2023-12 16460 16476