Mono- and cross-lingual evaluation of representation language models on less-resourced languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AH8HCMKZH" target="_blank" >RIV/00216208:11320/26:H8HCMKZH - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.csl.2025.101852" target="_blank" >http://dx.doi.org/10.1016/j.csl.2025.101852</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2025.101852" target="_blank" >10.1016/j.csl.2025.101852</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Mono- and cross-lingual evaluation of representation language models on less-resourced languages

Popis výsledku v původním jazyce

The current dominance of large language models in natural language processing is based on their contextual awareness. For text classification, text representation models, such as ELMo, BERT, and BERT derivatives, are typically fine-tuned for a specific problem. Most existing work focuses on English; in contrast, we present a large-scale multilingual empirical comparison of several monolingual and multilingual ELMo and BERT models using 14 classification tasks in nine languages. The results show, that the choice of best model largely depends on the task and language used, especially in a cross-lingual setting. In monolingual settings, monolingual BERT models tend to perform the best among BERT models. Among ELMo models, the ones trained on large corpora dominate. Cross-lingual knowledge transfer is feasible on most tasks already in a zero-shot setting without losing much performance. © 2025 The Authors

Název v anglickém jazyce

Mono- and cross-lingual evaluation of representation language models on less-resourced languages

Popis výsledku anglicky

The current dominance of large language models in natural language processing is based on their contextual awareness. For text classification, text representation models, such as ELMo, BERT, and BERT derivatives, are typically fine-tuned for a specific problem. Most existing work focuses on English; in contrast, we present a large-scale multilingual empirical comparison of several monolingual and multilingual ELMo and BERT models using 14 classification tasks in nine languages. The results show, that the choice of best model largely depends on the task and language used, especially in a cross-lingual setting. In monolingual settings, monolingual BERT models tend to perform the best among BERT models. Among ELMo models, the ones trained on large corpora dominate. Cross-lingual knowledge transfer is feasible on most tasks already in a zero-shot setting without losing much performance. © 2025 The Authors

Druh

J_SC - Článek v periodiku v databázi SCOPUS

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

2026

Kód důvěrnosti údajů

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

Název periodika

Computer Speech and Language

ISSN

0885-2308

e-ISSN

—

Svazek periodika

95

Číslo periodika v rámci svazku

2026

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

25

Strana od-do

101852

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105009701388