Soft Language Prompts for Language Transfer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0194218" target="_blank" >RIV/00216305:26230/26:0194218 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.naacl-long.517/" target="_blank" >https://aclanthology.org/2025.naacl-long.517/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.naacl-long.517" target="_blank" >10.18653/v1/2025.naacl-long.517</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Soft Language Prompts for Language Transfer

Popis výsledku v původním jazyce

Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination of parameter-efficient fine-tuning methods. We systematically explore strategies for enhancing cross-lingual transfer through the incorporation of language-specific and task-specific adapters and soft prompts. We present a detailed investigation of various combinations of these methods, exploring their efficiency across 16 languages, focusing on 10 mid- and low-resource languages. We further present to our knowledge the first use of soft prompts for language transfer, a technique we call soft language prompts. Our findings demonstrate that in contrast to claims of previous work, a combination of language and task adapters does not always work best; instead, combining a soft language prompt with a task adapter outperforms most configurations in many cases.

Název v anglickém jazyce

Soft Language Prompts for Language Transfer

Popis výsledku anglicky

Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination of parameter-efficient fine-tuning methods. We systematically explore strategies for enhancing cross-lingual transfer through the incorporation of language-specific and task-specific adapters and soft prompts. We present a detailed investigation of various combinations of these methods, exploring their efficiency across 16 languages, focusing on 10 mid- and low-resource languages. We further present to our knowledge the first use of soft prompts for language transfer, a technique we call soft language prompts. Our findings demonstrate that in contrast to claims of previous work, a combination of language and task adapters does not always work best; instead, combining a soft language prompt with a task adapter outperforms most configurations in many cases.

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

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

ISBN

979-8-8917-6189-6

ISSN

—

e-ISSN

—

Počet stran výsledku

19

Strana od-do

10294-10313

Název nakladatele

Association for Computational Linguistics

Místo vydání

Albuquerque

Místo konání akce

Albuquerque, New Mexico

Datum konání akce

29. 4. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001611654000198