mlsanityData to 14 Oct 2026

OCR Post Correction for Endangered Language Texts

arXiv 2011.05402 ↗First posted 10 Nov 2020cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

There is little to no data available to build natural language processing models for most endangered languages. However, textual data in these languages often exists in formats that are not machine-readable, such as paper books and scanned images. In this work, we address the task of extracting text from these resources. We create a benchmark dataset of transcriptions for scanned books in three critically endangered languages and present a systematic analysis of how general-purpose OCR tools are not robust to the data-scarce setting of endangered languages. We develop an OCR post-correction method tailored to ease training in this data-scarce setting, reducing the recognition error rate by 34% on average across the three languages.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 8; 2024: 4; 2025: 2; 2026: 5.

31 papers.

Sort:

By area:

  1. 2021OCR-free Document Understanding Transformercited by 407
  2. 2021Robust Open-Vocabulary Translation from Visual Text Representationscited by 47
  3. 2022Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptationcited by 44
  4. 2023XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languagescited by 34
  5. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  6. 2023A Material Lens on Coloniality in NLPcited by 21
  7. 2022How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Languagecited by 19
  8. 2023GlotScript: A Resource and Tool for Low Resource Writing System Identificationcited by 15
  9. 2022Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Penscited by 13
  10. 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correctioncited by 12
  11. 2023Efficient OCR for Building a Diverse Digital Historycited by 10
  12. 2021Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Modelscited by 8
19 more
  1. 2023Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Modelscited by 7
  2. 2024Extracting Training Data from Document-Based VQA Modelscited by 6
  3. 2022OCR Improves Machine Translation for Low-Resource Languagescited by 5
  4. 2025PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracycited by 5
  5. 2023User-Centric Evaluation of OCR Systems for Kwak'walacited by 4
  6. 2021Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcriptioncited by 3
  7. 2024Post-OCR Text Correction for Bulgarian Historical Documentscited by 3
  8. 2024RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languagescited by 3
  9. 2022Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languagescited by 2
  10. 2026synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barriercited by 2
  11. 2026A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documentscited by 2
  12. 2023Noisy Parallel Data Alignmentcited by 1
  13. 2024CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Modelscited by 1
  14. 2022Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondicited by 0
  15. 2023DUBLIN -- Document Understanding By Language-Image Networkcited by 0
  16. 2025Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Textscited by 0
  17. 2026Low-Resource Heuristics for Bahnaric Optical Character Recognition Improvementcited by 0
  18. 2026Structured Layout Priors for Robust Out-of-Distribution Visual Document Understandingcited by 0
  19. 2026Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scalingcited by 0