Publications

H. Mohebbi, W. Zuidema, G. Chrupała, A. Alishahi. Quantifying Context Mixing in Transformers. EACL 2023. [Paper] [Code] [Blog] [Demo]

A. Modarressi, H. Mohebbi, M. T. Pilehvar. AdapLeR: Speeding up Inference by Adaptive Length Reduction. ACL 2022. [Paper] [Code] [Blog]

M. Fayyaz, E. Aghazadeh, A. Modarressi, H. Mohebbi, M. T. Pilehvar. Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations. BlackboxNLP (EMNLP 2021). [Paper]

H. Mohebbi, A. Modarressi, M. T. Pilehvar. Exploring the Role of BERT Token Representations to Explain Sentence Probing Results. EMNLP 2021. [Paper] [Code] [Blog]