1 citations · 1 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023
Lazy-k: Decoding for Constrained Token Classification
Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo +2
We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of to…
cs.CL2023
Estimating Post-OCR Denoising Complexity on Numerical Texts
Arthur Hemmer, Jérôme Brachat, Mickaël Coustaty +1
Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as oppose…