Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AD7DMBLYZ" target="_blank" >RIV/00216208:11320/26:D7DMBLYZ - isvavai.cz</a>

Výsledek na webu

<a href="http://arxiv.org/abs/2501.14491" target="_blank" >http://arxiv.org/abs/2501.14491</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2501.14491" target="_blank" >10.48550/arXiv.2501.14491</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter

Popis výsledku v původním jazyce

Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses on a small set of languages from a few language families and/or a single task. It is still an open question how these findings extend to a wider variety of languages and tasks. In this work, we analyze cross-lingual transfer for 263 languages from a wide variety of language families. Moreover, we include three popular NLP tasks: POS tagging, dependency parsing, and topic classification. Our findings indicate that the effect of linguistic similarity on transfer performance depends on a range of factors: the NLP task, the (mono- or multilingual) input representations, and the definition of linguistic similarity.

Název v anglickém jazyce

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter

Popis výsledku anglicky

Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses on a small set of languages from a few language families and/or a single task. It is still an open question how these findings extend to a wider variety of languages and tasks. In this work, we analyze cross-lingual transfer for 263 languages from a wide variety of language families. Moreover, we include three popular NLP tasks: POS tagging, dependency parsing, and topic classification. Our findings indicate that the effect of linguistic similarity on transfer performance depends on a range of factors: the NLP task, the (mono- or multilingual) input representations, and the definition of linguistic similarity.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů