“Average” Approximates “First Principal Component”? An Empirical Analysis on Representations from Neural Language Models

“Average” Approximates “First Principal Component”? An Empirical Analysis on Representations from Neural Language Models Zihan Wang author Chengyu Dong author Jingbo Shang author 2021-11 text Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Marie-Francine Moens editor Xuanjing Huang editor Lucia Specia editor Scott Wen-tau Yih editor Association for Computational Linguistics Online and Punta Cana, Dominican Republic conference publication wang-etal-2021-average 10.18653/v1/2021.emnlp-main.453 https://aclanthology.org/2021.emnlp-main.453/ 2021-11 5594 5603