Litcius/Paper detail

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

2022Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies12 citationsDOIOpen Access PDF

Abstract

Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Topics & Concepts

Security tokenComputer scienceTransformerEncoderAttributionEngineeringElectrical engineeringComputer networkPsychologyVoltageOperating systemSocial psychologyTopic ModelingNatural Language Processing TechniquesExplainable Artificial Intelligence (XAI)
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers | Litcius