Search Results for author: Ehsan Aghazadeh

Found 5 papers, 2 papers with code

DecompX: Explaining Transformers Decisions by Propagating Token Decomposition

1 code implementation5 Jun 2023 Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

An emerging solution for explaining Transformer-based models is to use vector-based analysis on how the representations are formed.

Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages

1 code implementation ACL 2022 Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh

Large pre-trained language models (PLMs) are therefore assumed to encode metaphorical knowledge useful for NLP systems.

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

no code implementations13 Sep 2021 Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar

Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models.

Cannot find the paper you are looking for? You can Submit a new open access paper.