Error distributions estimated from text repetitions enable training of denoising autoencoders that improve OCR post-correction on historical Finnish newspapers without manual training data.
write newline
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2019 2representative citing papers
Presents multitask variational sequential labelers using latent variables for word prediction and label discrimination that outperform baselines on 8 datasets and benefit from unlabeled data.
citing papers explorer
-
Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction
Error distributions estimated from text repetitions enable training of denoising autoencoders that improve OCR post-correction on historical Finnish newspapers without manual training data.
-
Variational Sequential Labelers for Semi-Supervised Learning
Presents multitask variational sequential labelers using latent variables for word prediction and label discrimination that outperform baselines on 8 datasets and benefit from unlabeled data.