English

Less is More: The Effectiveness of Compact Typological Language Representations

Computation and Language 2025-09-25 v1

Abstract

Linguistic feature datasets such as URIEL+ are valuable for modelling cross-lingual relationships, but their high dimensionality and sparsity, especially for low-resource languages, limit the effectiveness of distance metrics. We propose a pipeline to optimize the URIEL+ typological feature space by combining feature selection and imputation, producing compact yet interpretable typological representations. We evaluate these feature subsets on linguistic distance alignment and downstream tasks, demonstrating that reduced-size representations of language typology can yield more informative distance metrics and improve performance in multilingual NLP applications.

Keywords

Cite

@article{arxiv.2509.20129,
  title  = {Less is More: The Effectiveness of Compact Typological Language Representations},
  author = {York Hay Ng and Phuong Hanh Hoang and En-Shiun Annie Lee},
  journal= {arXiv preprint arXiv:2509.20129},
  year   = {2025}
}

Comments

Accepted to EMNLP 2025 Main Conference

R2 v1 2026-07-01T05:54:10.456Z