Tom Elliott<p>New paper on machine learning for <a href="https://hcommons.social/tags/epigraphy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epigraphy</span></a></p><p>Assael, Yannis, Thea Sommerschield, Alison Cooley, et al. “Contextualizing Ancient Texts with Generative Neural Networks.” Nature, July 23, 2025, 1–7. <a href="https://doi.org/10.1038/s41586-025-09292-5" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.1038/s41586-025-092</span><span class="invisible">92-5</span></a>.</p><p>"Human history is born in writing. Inscriptions are among the earliest written forms, and offer direct insights into the thought, language and history of ancient civilizations. Historians capture these insights by identifying parallels—inscriptions with shared phrasing, function or cultural setting—to enable the contextualization of texts within broader historical frameworks, and perform key tasks such as restoration and geographical or chronological attribution1. However, current digital methods are restricted to literal matches and narrow historical scopes. Here we introduce Aeneas, a generative neural network for contextualizing ancient texts. Aeneas retrieves textual and contextual parallels, leverages visual inputs, handles ..."</p><p><a href="https://hcommons.social/tags/ancientHistory" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ancientHistory</span></a> <a href="https://hcommons.social/tags/classics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>classics</span></a> <a href="https://hcommons.social/tags/Latin" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Latin</span></a></p>