Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511609" target="_blank" >RIV/00216208:11320/25:10511609 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.ijcnlp-srw.18/" target="_blank" >https://aclanthology.org/2025.ijcnlp-srw.18/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems

Popis výsledku v původním jazyce

While Large Language Models (LLMs) have shown remarkable performance in various Natural Language Processing (NLP) tasks, their effectiveness seem to be heavily biased toward high-resource languages. This proposal aims to address this gap by developing efficient training strategies for low-resource languages. We propose various techniques for efficient learning in simluated low-resource settings for English. We then plan to adapt these methods for low-resource languages. We plan to experiment with both natural language generation and understanding models. We evaluate the models on similar benchmarks as the BabyLM challenge for English. For other languages, we plan to use treebanks and translation techniques to create our own silver test set to evaluate the low-resource LMs.

Název v anglickém jazyce

Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems

Popis výsledku anglicky

While Large Language Models (LLMs) have shown remarkable performance in various Natural Language Processing (NLP) tasks, their effectiveness seem to be heavily biased toward high-resource languages. This proposal aims to address this gap by developing efficient training strategies for low-resource languages. We propose various techniques for efficient learning in simluated low-resource settings for English. We then plan to adapt these methods for low-resource languages. We plan to experiment with both natural language generation and understanding models. We evaluate the models on similar benchmarks as the BabyLM challenge for English. For other languages, we plan to use treebanks and translation techniques to create our own silver test set to evaluate the low-resource LMs.

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

R - Projekt Ramcoveho programu EK

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics

ISBN

979-8-89176-304-3

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

209-217

Název nakladatele

Association for Computational Linguistics

Místo vydání

Kerrville, TX, USA

Místo konání akce

Mumbai, India

Datum konání akce

20. 12. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—