The Impact of Language Adapters in Cross-Lingual Transfer for NLU

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A3ABFHWDN" target="_blank" >RIV/00216208:11320/25:3ABFHWDN - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188800351&partnerID=40&md5=c94df610721d9b75fee8d27b094b9e5f" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188800351&partnerID=40&md5=c94df610721d9b75fee8d27b094b9e5f</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

The Impact of Language Adapters in Cross-Lingual Transfer for NLU

Popis výsledku v původním jazyce

Modular deep learning has been proposed for the efficient adaption of pre-trained models to new tasks, domains and languages. In particular, combining language adapters with task adapters has shown potential where no supervised data exists for a language. In this paper, we explore the role of language adapters in zero-shot cross-lingual transfer for natural language understanding (NLU) benchmarks. We study the effect of including a target-language adapter in detailed ablation studies with two multilingual models and three multilingual datasets. Our results show that the effect of target-language adapters is highly inconsistent across tasks, languages and models. Retaining the source-language adapter instead often leads to an equivalent, and sometimes to a better, performance. Removing the language adapter after training has only a weak negative effect, indicating that the language adapters do not have a strong impact on the predictions. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

The Impact of Language Adapters in Cross-Lingual Transfer for NLU

Popis výsledku anglicky

Modular deep learning has been proposed for the efficient adaption of pre-trained models to new tasks, domains and languages. In particular, combining language adapters with task adapters has shown potential where no supervised data exists for a language. In this paper, we explore the role of language adapters in zero-shot cross-lingual transfer for natural language understanding (NLU) benchmarks. We study the effect of including a target-language adapter in detailed ablation studies with two multilingual models and three multilingual datasets. Our results show that the effect of target-language adapters is highly inconsistent across tasks, languages and models. Retaining the source-language adapter instead often leads to an equivalent, and sometimes to a better, performance. Removing the language adapter after training has only a weak negative effect, indicating that the language adapters do not have a strong impact on the predictions. © 2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

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

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

MOOMIN - Workshop Modular Open Multiling. NLP, Proc. Workshop

ISBN

979-889176084-4

ISSN

—

e-ISSN

—

Počet stran výsledku

20

Strana od-do

24-43

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

St. Julian's

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—