Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy. Transformer Feed-Forward Layers Are Key-Value Memories. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. pages 5484-5495, Association for Computational Linguistics, 2021. [doi]
@inproceedings{GevaSBL21, title = {Transformer Feed-Forward Layers Are Key-Value Memories}, author = {Mor Geva and Roei Schuster and Jonathan Berant and Omer Levy}, year = {2021}, url = {https://aclanthology.org/2021.emnlp-main.446}, researchr = {https://researchr.org/publication/GevaSBL21}, cites = {0}, citedby = {0}, pages = {5484-5495}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021}, editor = {Marie-Francine Moens and Xuanjing Huang and Lucia Specia and Scott Wen-tau Yih}, publisher = {Association for Computational Linguistics}, }