[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290183-105":59,"doc-detail-290183-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","machine-learning-for-ancient-languages-a-survey","Machine Learning for Ancient Languages - A Survey","","Machine Learning for Ancient Languages: A Survey presents a comprehensive overview of published research applying machine learning to the study of ancient texts across languages, scripts, and media spanning more than three and a half millennia. It addresses challenges in decipherment, restoration, attribution, linguistic analysis, textual criticism, translation, and related tasks. The work contributes a taxonomy of tasks, maps the interdisciplinary space between humanities and machine learning, emphasizes collaboration between specialists, and highlights promising future research directions.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-for-ancient-languages-a-survey/290183/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-for-ancient-languages-a-survey/290183.png","ImageObject",300,407,{"name":92,"@type":93},"Himbo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-19","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is the main purpose of this survey on machine learning for ancient languages?","Question",{"text":113,"@type":114},"It provides a comprehensive survey of published research using machine learning to study ancient texts written in any language, script, and medium.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which tasks does the survey focus on for ancient document analysis?",{"text":118,"@type":114},"It introduces a taxonomy covering digitization, restoration, attribution, linguistic analysis, textual criticism, translation, and decipherment.",{"name":120,"@type":111,"acceptedAnswer":121},"What major contributions does the work claim to make?",{"text":122,"@type":114},"It maps the interdisciplinary field between humanities and machine learning, stresses collaboration between specialists, and outlines promising directions for future work.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290183,1789640884,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},687197100911,"https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697","Machine Learning for Ancient Languages: A Survey  \nThea Sommerschield􀀃  \nCa' Foscari University of Venice Department of Humanities [thea.sommerschield@unive.it](thea.sommerschield@unive.it)  \nYannis Assael􀀃  \nGoogle DeepMind [yannisassael@google.com](yannisassael@google.com)  \nJohn Pavlopoulos􀀃 Athens University of Economics and Business  \n[annis@aueb.gr](annis@aueb.gr)  \nVanessa Stefanak Google DeepMind  \nAndrew Senior Google DeepMind [andrewsenior@google.com](andrewsenior@google.com)  \nChris Dyer Google DeepMind [cdyer@google.com](cdyer@google.com)  \nJohn Bodel Brown University Classics Faculty  \nJohn [Bodel@brown.edu](Bodel@brown.edu)  \nJonathan Prag University of Oxford Faculty of Classics  \n[jonathan.prag@merton.ox.ac.uk](jonathan.prag@merton.ox.ac.uk)  \n􀀃 Thea Sommerschield, Yannis Assael, and John Pavlopoulos contributed equally to this work. To whom [correspondence should be addressed. E-mail:](correspondence should be addressed. E-mail: yannisassael@google.com)[ yannisassael@google.com](correspondence should be addressed. E-mail: yannisassael@google.com), [thea.sommerschield@unive.it](thea.sommerschield@unive.it), [annis@aueb.gr](annis@aueb.gr)  \nAction Editor: Nianwen Xue. Submission received: 17 January 2023; revised version received: 20 March 2023;  \naccepted for publication: 16 April 2023 .  \n[https://doi.org/10.1162/coli](https://doi.org/10.1162/coli) a 00481  \n© 2023 Association for Computational Linguistics  \nPublished under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license  \nDownloaded from [http://direct.mit.edu/coli/article-pdf/49/3/703/2177413/coli_a_00481.pdf by guest on 30 January 2024](http://direct.mit.edu/coli/article-pdf/49/3/703/2177413/coli_a_00481.pdf by guest on 30 January 2024)  \nComputational Linguistics Volume 49, Number 3  \nIon Androutsopoulos Athens University of Economics and Business Department of Informatics [ion@aueb.gr](ion@aueb.gr)  \nNando de Freitas Google DeepMind [nandodefreitas@google.com](nandodefreitas@google.com)  \nAncient 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 promotesand supports the continued collaborative impetus between the humanities and machine learning.  \n1. Introduction  \nAncient languages are key conveyors and repositories of ancient civilizations, as they encode the thought, cultures, and histories of the past. The texts that preserve these languages were written over the centuries on a variety of media (bone, metal, palm leaf, paper, papyri, parchment, potsherds, stone) and in diff","cbCaisQCYke3Pwwm","https://ap.wps.com/l/cbCaisQCYke3Pwwm","pdf",526465,45,"English","# Introduction\n## Survey scope and motivation\n## Taxonomy of tasks in ancient document study\n## Major contributions and future directions\n## Background: models, datasets, and rising research activity","[{\"question\":\"What is the main purpose of this survey on machine learning for ancient languages?\",\"answer\":\"It provides a comprehensive survey of published research using machine learning to study ancient texts written in any language, script, and medium.\"},{\"question\":\"Which tasks does the survey focus on for ancient document analysis?\",\"answer\":\"It introduces a taxonomy covering digitization, restoration, attribution, linguistic analysis, textual criticism, translation, and decipherment.\"},{\"question\":\"What major contributions does the work claim to make?\",\"answer\":\"It maps the interdisciplinary field between humanities and machine learning, stresses collaboration between specialists, and outlines promising directions for future work.\"}]","Machine Learning for Ancient Languages - A Survey | PDF",113]