Machine Learning for Ancient Languages: A Survey
Машинное обучение для древних языков: обзор
2023-01-01
SCID: 54.1/2f48vcet
Discuss with AI
ancient textsauthorship attributiondeciphermentmachine learningtext restoration
Figures from the paper
Abstract (AI)
Abstract Ancient languages preserve the cultures and histories of the past. However, their study is fraught with difficulties, and experts must tackle a range of challenging text-based tasks, from deciphering lost languages to restoring damaged inscriptions, to determining the authorship of works of literature. Technological aids have long supported the study of ancient texts, but in recent years advances in artificial intelligence and machine learning have enabled analyses on a scale and in a detail that are reshaping the field of humanities, similarly to how microscopes and telescopes have contributed to the realm of science. This article aims to provide a comprehensive survey of published research using machine learning for the study of ancient texts written in any language, script, and medium, spanning over three and a half millennia of civilizations around the ancient world. To analyze the relevant literature, we introduce a taxonomy of tasks inspired by the steps involved in the study of ancient documents: digitization, restoration, attribution, linguistic analysis, textual criticism, translation, and decipherment. This work offers three major contributions: first, mapping the interdisciplinary field carved out by the synergy between the humanities and machine learning; second, highlighting how active collaboration between specialists from both fields is key to producing impactful and compelling scholarship; third, highlighting promising directions for future work in this field. Thus, this work promotes and supports the continued collaborative impetus between the humanities and machine learning.
Key Findings
1
Active collaboration between domain experts and machine-learning specialists is identified as essential for impactful scholarship, with promising directions outlined for future research.
2
It organizes the field into seven task categories: digitization, restoration, attribution, linguistic analysis, textual criticism, translation, and decipherment.
3
Machine learning enables ancient-text analysis at scales and levels of detail that are reshaping humanities research.
4
The survey covers machine-learning research on ancient texts across languages, scripts, media, and more than three and a half millennia of civilizations.
5
The survey maps the interdisciplinary field formed by collaboration between humanities specialists and machine-learning researchers.
Research Object
ancient texts and documents written in any language, script, and medium
Research Subject
the applications and research tasks of machine learning for digitization, restoration, attribution, linguistic analysis, textual criticism, translation, and decipherment of ancient texts
Publication Details
Publication Date
2023-01-01
Journal
Publisher
ISSN
Cited by
108
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
Deep Residual Learning for Image Recognition2016
Distributed Representations of Words and Phrases and their Compositionality2013
Generative adversarial networks2020
The FAIR Guiding Principles for scientific data management and stewardship2016
Sequence to Sequence Learning with Neural Networks2014
Representation Learning: A Review and New Perspectives2013
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014
PaLM: Scaling Language Modeling with Pathways2022
Restoring and attributing ancient texts using deep neural networks2022