Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition

1 code implementation • 21 Jul 2021 • Mohamed Ali Souibgui, Alicia Fornés, Yousri Kessentini, Beáta Megyesi

Since this retraining would require annotation of thousands of handwritten symbols together with their bounding boxes, we propose to avoid such human effort through an unsupervised progressive learning approach that automatically assigns pseudo-labels to the non-annotated data.

Few-Shot Learning Handwriting Recognition +1

Decipherment of Historical Manuscript Images

1 code implementation • 9 Oct 2018 • Xusen Yin, Nada Aldarrab, Beáta Megyesi, Kevin Knight

European libraries and archives are filled with enciphered manuscripts from the early modern period.

Clustering Decipherment +1

EACL - Expansion of Abbreviations in CLinical text

no code implementations • WS 2014 • Lisa Tengstrand, Beáta Megyesi, Aron Henriksson, Martin Duneld, Maria Kvist