3 papers
cs.CL2021
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling
Marcin Namysl, Sven Behnke, Joachim Köhler
Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) p…
cs.CL2020
NAT: Noise-Aware Training for Robust Neural Sequence Labeling
Marcin Namysl, Sven Behnke, Joachim Köhler
Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an e…
cs.CV2019
Efficient, Lexicon-Free OCR using Deep Learning
Marcin Namysl, Iuliu Konya
Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging problem when text occurs in unconstrained environments, like natural scenes, due to geometrica…