Merve Tekgürler
PhD Candidate in History & MS Student in Symbolic Systems — Stanford University
Guest Lecture
LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models
Merve Tekgürler is a PhD candidate in History and an M.S. student in Symbolic Systems at Stanford University. She holds the inaugural Mellon/ACLS Dissertation Innovation Fellowship. Her dissertation focuses on the Ottoman-Polish borderlands in the long 18th century, examining Ottoman news and information networks and their impact on imperial knowledge production.
As part of her dissertation project, Merve is training a handwritten text recognition model for eighteenth-century Ottoman Turkish administrative sources. She has given presentations on the use of neural machine translation (NMT) and large language models (LLMs) to translate Ottoman Turkish into English, exploring the intersection of AI and historical research.