{"total":29,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2104.08211","title":"Robust Open-Vocabulary Translation from Visual Text Representations","created":"2021-04-16","cited_by_count":47,"area":null},{"id":"2203.09435","title":"Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation","created":"2022-03-17","cited_by_count":44,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2204.11909","title":"How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language","created":"2022-04-25","cited_by_count":19,"area":null},{"id":"2309.13320","title":"GlotScript: A Resource and Tool for Low Resource Writing System Identification","created":"2023-09-23","cited_by_count":15,"area":null},{"id":"2202.07036","title":"Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens","created":"2022-02-14","cited_by_count":13,"area":null},{"id":"2111.02622","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","created":"2021-11-04","cited_by_count":12,"area":null},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2109.06264","title":"Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2202.13274","title":"OCR Improves Machine Translation for Low-Resource Languages","created":"2022-02-27","cited_by_count":5,"area":null},{"id":"2505.20429","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2302.13410","title":"User-Centric Evaluation of OCR Systems for Kwak'wala","created":"2023-02-26","cited_by_count":4,"area":null},{"id":"2112.08692","title":"Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2409.00527","title":"Post-OCR Text Correction for Bulgarian Historical Documents","created":"2024-08-31","cited_by_count":3,"area":null},{"id":"2412.15248","title":"RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages","created":"2024-12-14","cited_by_count":3,"area":null},{"id":"2203.09632","title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2601.16113","title":"synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.25761","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2301.09685","title":"Noisy Parallel Data Alignment","created":"2023-01-23","cited_by_count":1,"area":null},{"id":"2404.02408","title":"CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2211.16172","title":"Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2506.01775","title":"Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2601.02965","title":"Low-Resource Heuristics for Bahnaric Optical Character Recognition Improvement","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2608.03842","title":"Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}