Holle Meding<p>📰 Classifying Genre in Historical Medical Periodicals</p><p>Next in line: Vera Danilova presents her work on genre classification in digitized periodicals from European patient organizations (1951–1990) using <a href="https://mastodon.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> as part of the <a href="https://mastodon.social/tags/ActDisease" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ActDisease</span></a> project. </p><p>🔹 XLM-RoBERTa (UDM) led Q&amp;A tasks with 32% more correct answers than mBERT/hmBERT.<br>🔹 hmBERT (UDM) topped Administrative classification (+16%)<br>🔹 CORE-based models excelled in legal genre prediction. </p><p><a href="https://mastodon.social/tags/DigitalHumanities" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DigitalHumanities</span></a> <span class="h-card" translate="no"><a href="https://wisskomm.social/@tuberlin" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>tuberlin</span></a></span> <a href="https://mastodon.social/tags/classification" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>classification</span></a> <a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p>