Publications
Confidence-Aware Document OCR Error Detection
Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo, Jean-Marc Ogier
Document Analysis Systems: 16th IAPR International Workshop, DAS 2024
Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error detection capabilities. This work underscores the importance of OCR confidence scores in improving detection accuracy and reveals substantial disparities in performance between commercial and open-source OCR technologies.
Lazy-k: Decoding for Constrained Information Extraction
Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo, Jérôme Brachat, Jean-Marc Ogier
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-k. Our findings demonstrate that constrained decoding approaches can significantly improve the models' performances, especially when using smaller models. The Lazy-k approach allows for more flexibility between decoding time and accuracy.
Estimating Post-OCR Denoising Complexity on Numerical Texts
Arthur Hemmer, Jérôme Brachat, Mickaël Coustaty, Jean-Marc Ogier
Communications in Computer and Information Science, Volume 1863, 2023
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 opposed to documents of numerical nature such as invoices, payslips, medical certificates, etc. To evaluate the OCR post-processing difficulty of these datasets, we propose a method to estimate the denoising complexity of a text and evaluate it on several datasets of varying nature, and show that texts of numerical nature have a significant disadvantage. We evaluate the estimated complexity ranking with respect to the error rates of modern-day denoising approaches to show the validity of our estimator.