From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction
Not on the map. Why?
Abstract (arXiv)
A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We present a fully automatic unsupervised way of extracting parallel data for training a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 1; 2023: 1; 2024: 1.
7 papers.
- 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correctioncited by 12
- 2021Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labelingcited by 8
- 2021Neural Language Models for Nineteenth-Century Englishcited by 7
- 2022An Assessment of the Impact of OCR Noise on Language Modelscited by 5
- 2021Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcriptioncited by 3
- 2023Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Textscited by 2
- 2024Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentationcited by 1
- 2024Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation26 Jul 2024
- 2023Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts30 Jul 2023
- 2022An Assessment of the Impact of OCR Noise on Language Models26 Jan 2022
- 2021Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription16 Dec 2021
- 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correction4 Nov 2021
- 2021Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling25 May 2021
- 2021Neural Language Models for Nineteenth-Century English24 May 2021