A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base

TL;DR

This study critically examines the URIEL knowledge base, revealing issues with its reproducibility, ambiguity in language similarity calculations, and significant missing data for many languages, impacting NLP research reliability.

Contribution

It provides a detailed analysis of URIEL's limitations, highlighting ambiguity in its methods and the extent of missing typological data, which affects its use in multilingual NLP research.

Findings

URIEL has ambiguity in language distance calculations.

31% of languages lack typological feature data in URIEL.

Missing data undermines URIEL's reliability for low-resource languages.

Abstract

In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. In this study, we focus on a widely used typological knowledge base, URIEL, which aggregates linguistic information into numeric vectors. Specifically, we delve into the soundness and reproducibility of the approach taken by URIEL in quantifying language similarity. Our analysis reveals URIEL's ambiguity in calculating language distances and in handling missing values. Moreover, we find that URIEL does not provide any information about typological features for 31\% of the languages it represents, undermining the reliabilility of the database, particularly on low-resource languages. Our literature review suggests URIEL and lang2vec are used in papers on diverse NLP tasks, which motivates us to rigorously verify the database as the effectiveness of these works depends on the reliability of the information the tool provides.