Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+

TL;DR

This paper enhances the URIEL+ linguistic knowledge base by adding script vectors, expanding language coverage, and improving feature imputation, thereby supporting better cross-lingual transfer especially for low-resource languages.

Contribution

The paper introduces new script vectors, integrates Glottolog for broader language coverage, and improves lineage imputation, significantly reducing data sparsity in URIEL+.

Findings

Feature sparsity reduced by 14%

Language coverage increased by up to 19,015 languages (1,007%)

Imputation quality improved by up to 35%

Abstract

The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing feature types, incomplete language entries, and limited genealogical coverage) remains prevalent. This limits the usefulness of URIEL+ in cross-lingual transfer, particularly for supporting low-resource languages. To address this sparsity, we extend URIEL+ by introducing script vectors to represent writing system properties for 7,488 languages, integrating Glottolog to add 18,710 additional languages, and expanding lineage imputation for 26,449 languages by propagating typological and script features across genealogies. These improvements reduce feature sparsity by 14% for script vectors, increase language coverage by up to 19,015 languages (1,007%), and boost imputation quality metrics by up to 35%. Our benchmark on cross-lingual transfer tasks (oriented around low-resource languages) shows occasionally divergent performance compared to URIEL+, with performance gains up to 6% in certain setups.