| Challenge: | Current optical character recognition (OCR) systems are poorly extensible to low-resource document collections, as learning a language-vision model requires extensive labeled sequences and compute. |
| Approach: | They propose to model optical character recognition as a character level image retrieval problem using a contrastively trained vision encoder. |
| Outcome: | The proposed model is more sample efficient and extensible than existing architectures, enabling accurate OCR in settings where existing solutions fail. |
Similar Papers
EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Existing OCR engines fail to provide accurate, cost-effective and sample-efficient character recognition for public domain documents. |
| Approach: | EffOCR is an open-source optical character recognition package that is accurate, cheap to deploy and sample efficient to customize to novel collections, languages, and character sets. |
| Outcome: | EffOCR model trains character retrieval problem and scales to novel collections, languages, and character sets. |
LOCR: Location-Guided Transformer for Optical Character Recognition (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Academic documents are packed with texts, equations, tables, and figures, posing challenges for accurate OCR results. |
| Approach: | They propose a model that integrates location guiding into the transformer architecture during autoregression. |
| Outcome: | The proposed model outperforms existing methods on an original large-scale dataset comprising 53M text-location pairs from 89K academic document pages. |
Gold Standard Bangla OCR Dataset: An In-Depth Look at Data Preprocessing and Annotation Processes (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing datasets designed specifically for the Bengali language have been limited. |
| Approach: | They propose to use a large collection of labeled Bangla text image datasets to improve the performance of Bangla OCR. |
| Outcome: | The proposed system is the most extensive gold standard corpus for Bangla characters and words, comprising over 4 million human-annotated images. |
How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR (2020.lrec-1)
Copied to clipboard
| Challenge: | Recent advances in Optical Character Recognition and Handwritten Text Recognition have led to more accurate text recognition of historical documents. |
| Approach: | They propose to build a ground truth for a German-language newspaper published in black letter . they also evaluate the performance of different OCR engines and estimate how much data is needed to achieve high-quality OCR results. |
| Outcome: | The proposed model can recognise black letter text and performs well on data they have not seen during training. |
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite advances in Large Vision Language Models, a gap remains in their interpretability and performance. |
| Approach: | They identify the Optical Character Recognition Head (OCR Head) heads that are more efficient at recognizing text from images. |
| Outcome: | The Optical Character Recognition Head (OCR Head) is identified as the most efficient head for recognizing text from images. |
Evaluating Transformers for OCR Post-Correction in Early Modern Dutch Theatre (2025.coling-main)
Copied to clipboard
| Challenge: | a new study examines the effectiveness of two types of transformer models for OCR post-correction in early modern Dutch plays. |
| Approach: | They propose to use large generative models and sequence-to-sequence models for OCR post-correction in early modern Dutch plays. |
| Outcome: | The proposed model outperforms generative models on the OCR post-correction task . the model outpersforms the model with the lowest error rate on the historical English dataset . |
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)
Copied to clipboard
| Challenge: | Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images. |
| Approach: | They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency. |
| Outcome: | The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images. |
Neural OCR Post-Hoc Correction of Historical Corpora (2021.tacl-1)
Copied to clipboard
| Challenge: | Optical character recognition (OCR) is crucial for a deeper access to historical collections. |
| Approach: | They propose a neural approach based on a combination of recurrent (RNN) and deep convolutional network (ConvNet) to correct OCR transcription errors. |
| Outcome: | The proposed model reduces the word error rate of 32.3% by more than 89% on a historical book corpus in German language. |
Low-resource Post Processing of Noisy OCR Output for Historical Corpus Digitisation (L18-1)
Copied to clipboard
| Challenge: | 7.6% of the words in the original OCR text contain an error; fully manual correction would take thousands of hours due to the size of the corpus. |
| Approach: | They propose a post-processing system to efficiently correct OCR errors in a 2.7 million word Faroese corpus. |
| Outcome: | The proposed method reduces the word error rate to 1.3% with around 65 hours of human annotator work. |
A Lightweight Approach to a Giga-Corpus of Historical Periodicals: The Story of a Slovenian Historical Newspaper Collection (2024.lrec-main)
Copied to clipboard
| Challenge: | a curated corpus of Slovenian historical newspapers is a complex undertaking requiring multiple steps to prepare . a shoestring budget is required to produce a corpus that is billion-words in size . |
| Approach: | They propose a lightweight approach to producing high-quality corpora using OCR . they use noisy OCR-ed data from the National and University Library of Slovenia . |
| Outcome: | The proposed method produces a billion-word giga-corpus of Slovenian historical newspapers from the 18th, 19th and 20th centuries on a shoestring budget. |