Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription

no code implementations • Findings (NAACL) 2022 • Nikolai Vogler, Jonathan Parkes Allen, Matthew Thomas Miller, Taylor Berg-Kirkpatrick

We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription.

Language Modelling

BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts

no code implementations • 9 Jul 2019 • Benjamin Kiessling, Daniel Stökl Ben Ezra, Matthew Thomas Miller

The application of handwritten text recognition to historical works is highly dependant on accurate text line retrieval.

Handwritten Text Recognition Retrieval

Important New Developments in Arabographic Optical Character Recognition (OCR)

no code implementations • 28 Mar 2017 • Maxim Romanov, Matthew Thomas Miller, Sarah Bowen Savant, Benjamin Kiessling

The OpenITI team has achieved Optical Character Recognition (OCR) accuracy rates for classical Arabic-script texts in the high nineties.

Optical Character Recognition Optical Character Recognition (OCR)