AI Heap
Published on

URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base

arXiv:2409.18472 - [arXiv,PDF]
Authors
  • Name
    Aditya Khan
  • Name
    Mason Shipton
  • Name
    David Anugraha
  • Name
    Kaiyao Duan
  • Name
    Phuong H. Hoang
  • Name
    Eric Khiu
  • Name
    A. Seza Do\u{g}ru\"oz
  • Name
    En-Shiun Annie Lee
  • Affiliation
    University of Toronto, Canada
  • Affiliation
    Ontario Tech University, Canada
  • Affiliation
    University of Michigan, USA
  • Affiliation
  • Affiliation
    LT3, IDLab, Universiteit Gent, Belgium
URIEL is a knowledge base offering geographical, phylogenetic, and typological vector representations for 7970 languages. It includes distance measures between these vectors for 4005 languages, which are accessible via the lang2vec tool. Despite being frequently cited, URIEL is limited in terms of linguistic inclusion and overall usability. To tackle these challenges, we introduce URIEL+, an enhanced version of URIEL and lang2vec that addresses these limitations. In addition to expanding typological feature coverage for 2898 languages, URIEL+ improves the user experience with robust, customizable distance calculations to better suit the needs of users. These upgrades also offer competitive performance on downstream tasks and provide distances that better align with linguistic distance studies.