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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Toossi, Hasti, Huai, Guo Qing, Liu, Jinyu, Khiu, Eric, Doğruöz, A. Seza, Lee, En-Shiun Annie
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910452705918976
author Toossi, Hasti
Huai, Guo Qing
Liu, Jinyu
Khiu, Eric
Doğruöz, A. Seza
Lee, En-Shiun Annie
author_facet Toossi, Hasti
Huai, Guo Qing
Liu, Jinyu
Khiu, Eric
Doğruöz, A. Seza
Lee, En-Shiun Annie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11125
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base
Toossi, Hasti
Huai, Guo Qing
Liu, Jinyu
Khiu, Eric
Doğruöz, A. Seza
Lee, En-Shiun Annie
Computation and Language
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.
title A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base
topic Computation and Language
url https://arxiv.org/abs/2405.11125