@article{Ramirez-Orta_Xamena_Maguitman_Milios_Soto_2022, title={Post-OCR Document Correction with Large Ensembles of Character Sequence-to-Sequence Models}, volume={36}, url={https://ojs.aaai.org/index.php/AAAI/article/view/21369}, DOI={10.1609/aaai.v36i10.21369}, abstractNote={In this paper, we propose a novel method to extend sequence-to-sequence models to accurately process sequences much longer than the ones used during training while being sample- and resource-efficient, supported by thorough experimentation. To investigate the effectiveness of our method, we apply it to the task of correcting documents already processed with Optical Character Recognition (OCR) systems using sequence-to-sequence models based on characters. We test our method on nine languages of the ICDAR 2019 competition on post-OCR text correction and achieve a new state-of-the-art performance in five of them. The strategy with the best performance involves splitting the input document in character n-grams and combining their individual corrections into the final output using a voting scheme that is equivalent to an ensemble of a large number of sequence models. We further investigate how to weigh the contributions from each one of the members of this ensemble. Our code for post-OCR correction is shared at https://github.com/jarobyte91/post_ocr_correction.}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ramirez-Orta, Juan Antonio and Xamena, Eduardo and Maguitman, Ana and Milios, Evangelos and Soto, Axel J.}, year={2022}, month={Jun.}, pages={11192-11199} }