PHD: Pixel-Based Language Modeling of Historical Documents
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
PHD : Pixel-Based Language Modeling of Historical Documents. / Borenstein, Nadav; Rust, Phillip; Elliott, Desmond; Augenstein, Isabelle.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processin. Association for Computational Linguistics (ACL), 2023. s. 87–107.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - PHD
T2 - 2023 Conference on Empirical Methods in Natural Language Processing
AU - Borenstein, Nadav
AU - Rust, Phillip
AU - Elliott, Desmond
AU - Augenstein, Isabelle
PY - 2023
Y1 - 2023
N2 - The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents. We then pre-train our model, PHD, on a combination of synthetic scans and real historical newspapers from the 1700-1900 period. Through our experiments, we demonstrate that PHD exhibits high proficiency in reconstructing masked image patches and provide evidence of our model's noteworthy language understanding capabilities. Notably, we successfully apply our model to a historical QA task, highlighting its usefulness in this domain.
AB - The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents. We then pre-train our model, PHD, on a combination of synthetic scans and real historical newspapers from the 1700-1900 period. Through our experiments, we demonstrate that PHD exhibits high proficiency in reconstructing masked image patches and provide evidence of our model's noteworthy language understanding capabilities. Notably, we successfully apply our model to a historical QA task, highlighting its usefulness in this domain.
KW - cs.CL
U2 - 10.18653/v1/2023.emnlp-main.7
DO - 10.18653/v1/2023.emnlp-main.7
M3 - Article in proceedings
SP - 87
EP - 107
BT - Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processin
PB - Association for Computational Linguistics (ACL)
Y2 - 6 December 2023 through 10 December 2023
ER -
ID: 379722635