A Preliminary Analysis of Texts from Pre-Sargonic Lagaš
Developing a quantitative methodology for studying how the spatial relationships of cuneiform signs changes during one of the most foundational shifts in early writing.
A Transliteration Dataset of Sumerian Tablets
(1) Released a dataset mapping Unicode cuneiform glyphs to transliterations (91,606 tablets / 6,970,407 glyphs).
(2) Set naïve + transformer baselines on transliteration task, reaching 97.55 chrF on held-out transliteration.
Pioneering Deep Learning Approaches to Sumerian Cuneiform
Deep learning approaches to three cuneiform tasks: OCR, transliteration, and translation.
An AI-powered alternative to Overleaf. Close to launch, on hold during my MPhil.
Platform for extracting and managing structured data from commercial real estate legal documents.
A tool for annotating the cuneiform set texts I study in my classes.