@inproceedings{borenstein-etal-2023-phd,
title = "{PHD}: Pixel-Based Language Modeling of Historical Documents",
author = "Borenstein, Nadav and
Rust, Phillip and
Elliott, Desmond and
Augenstein, Isabelle",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.7/",
doi = "10.18653/v1/2023.emnlp-main.7",
pages = "87--107",
abstract = "The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels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Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents.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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borenstein-etal-2023-phd">
<titleInfo>
<title>PHD: Pixel-Based Language Modeling of Historical Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadav</namePart>
<namePart type="family">Borenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillip</namePart>
<namePart type="family">Rust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">borenstein-etal-2023-phd</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.7</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.7/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>87</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PHD: Pixel-Based Language Modeling of Historical Documents
%A Borenstein, Nadav
%A Rust, Phillip
%A Elliott, Desmond
%A Augenstein, Isabelle
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F borenstein-etal-2023-phd
%X 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.
%R 10.18653/v1/2023.emnlp-main.7
%U https://aclanthology.org/2023.emnlp-main.7/
%U https://doi.org/10.18653/v1/2023.emnlp-main.7
%P 87-107
Markdown (Informal)
[PHD: Pixel-Based Language Modeling of Historical Documents](https://aclanthology.org/2023.emnlp-main.7/) (Borenstein et al., EMNLP 2023)
ACL
- Nadav Borenstein, Phillip Rust, Desmond Elliott, and Isabelle Augenstein. 2023. PHD: Pixel-Based Language Modeling of Historical Documents. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 87–107, Singapore. Association for Computational Linguistics.