Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations Mohsen Fayyaz author Ehsan Aghazadeh author Ali Modarressi author Hosein Mohebbi author Mohammad Taher Pilehvar author 2021-11 text Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP Jasmijn Bastings editor Yonatan Belinkov editor Emmanuel Dupoux editor Mario Giulianelli editor Dieuwke Hupkes editor Yuval Pinter editor Hassan Sajjad editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication fayyaz-etal-2021-models 10.18653/v1/2021.blackboxnlp-1.29 https://aclanthology.org/2021.blackboxnlp-1.29/ 2021-11 375 388