Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
Published in Language Resources and Evaluation Conference (LREC) 2026, 2026
This paper extends URIEL+ by adding script vectors, integrating Glottolog to expand language coverage, and broadening lineage-based imputation. These additions reduce sparsity, increase language coverage, and make URIEL+ more complete for multilingual and low-resource language research.
Recommended citation: Mason Shipton, York Hay Ng, Aditya Khan, Phuong Hanh Hoang, Xiang Lu, A. Seza Dogruoz, and En-Shiun Annie Lee. 2026. Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+. In Proceedings of the Language Resources and Evaluation Conference (LREC) 2026.
Download Paper