Searching for Reasons of Transformers' Success: Memorization vs Generalization

Frantisek Trebuna, Kristína Szabová, Ondrej Bojar. Searching for Reasons of Transformers' Success: Memorization vs Generalization. In Kamil Ekstein, Frantisek Pártl, Miloslav Konopík, editors, Text, Speech, and Dialogue - 26th International Conference, TSD 2023, Pilsen, Czech Republic, September 4-6, 2023, Proceedings. Volume 14102 of Lecture Notes in Computer Science, pages 25-32, Springer, 2023. [doi]

Abstract

Abstract is missing.