IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2304.02737.html
   My bibliography  Save this paper

Efficient OCR for Building a Diverse Digital History

Author

Listed:
  • Jacob Carlson
  • Tom Bryan
  • Melissa Dell

Abstract

Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR) - which jointly learns a vision and language model - is poorly extensible to low-resource document collections, as learning a language-vision model requires extensive labeled sequences and compute. This study models OCR as a character level image retrieval problem, using a contrastively trained vision encoder. Because the model only learns characters' visual features, it is more sample efficient and extensible than existing architectures, enabling accurate OCR in settings where existing solutions fail. Crucially, the model opens new avenues for community engagement in making digital history more representative of documentary history.

Suggested Citation

  • Jacob Carlson & Tom Bryan & Melissa Dell, 2023. "Efficient OCR for Building a Diverse Digital History," Papers 2304.02737, arXiv.org, revised Jul 2024.
  • Handle: RePEc:arx:papers:2304.02737
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2304.02737
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Beach, Brian & Hanlon, W. Walker, 2022. "Historical Newspaper Data: A Researcher's Guide and Toolkit," CEPR Discussion Papers 17366, C.E.P.R. Discussion Papers.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Xinmei Yang & Abhishek Arora & Shao-Yu Jheng & Melissa Dell, 2023. "Quantifying Character Similarity with Vision Transformers," Papers 2305.14672, arXiv.org.
    2. Melissa Dell & Jacob Carlson & Tom Bryan & Emily Silcock & Abhishek Arora & Zejiang Shen & Luca D'Amico-Wong & Quan Le & Pablo Querubin & Leander Heldring, 2023. "American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers," Papers 2308.12477, arXiv.org.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Daniel J. Smith & Macy Scheck, 2023. "Examining the public interest rationale for regulating whiskey with the pure food and drugs act," Public Choice, Springer, vol. 196(1), pages 85-122, July.
    2. Melissa Dell & Jacob Carlson & Tom Bryan & Emily Silcock & Abhishek Arora & Zejiang Shen & Luca D'Amico-Wong & Quan Le & Pablo Querubin & Leander Heldring, 2023. "American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers," Papers 2308.12477, arXiv.org.
    3. Alex Armand & Paul Atwell & Joseph F. Gomes & Yannik Schenk, 2023. "It’s a Bird, it’s a Plane, it’s Superman! Using Mass Media to fight Intolerance," LIDAM Discussion Papers IRES 2023012, Université catholique de Louvain, Institut de Recherches Economiques et Sociales (IRES).
    4. Quentin Lippmann & Khushboo Surana, 2022. "The Hierarchy of Partner Preferences," Discussion Papers 22/08, Department of Economics, University of York.
    5. Melissa Dell, 2024. "Deep Learning for Economists," Papers 2407.15339, arXiv.org, revised Nov 2024.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2304.02737. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.