Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Thakur, Madhavendra
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.20584
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912407497998336
author Thakur, Madhavendra
author_facet Thakur, Madhavendra
contents No-resource languages - those with minimal or no digital representation - pose unique challenges for machine translation (MT). Unlike low-resource languages, which rely on limited but existent corpora, no-resource languages often have fewer than 100 sentences available for training. This work explores the problem of no-resource translation through three distinct workflows: fine-tuning of translation-specific models, in-context learning with large language models (LLMs) using chain-of-reasoning prompting, and direct prompting without reasoning. Using Owens Valley Paiute as a case study, we demonstrate that no-resource translation demands fundamentally different approaches from low-resource scenarios, as traditional approaches to machine translation, such as those that work for low-resource languages, fail. Empirical results reveal that, although traditional approaches fail, the in-context learning capabilities of general-purpose large language models enable no-resource language translation that outperforms low-resource translation approaches and rivals human translations (BLEU 0.45-0.6); specifically, chain-of-reasoning prompting outperforms other methods for larger corpora, while direct prompting exhibits advantages in smaller datasets. As these approaches are language-agnostic, they have potential to be generalized to translation tasks from a wide variety of no-resource languages without expert input. These findings establish no-resource translation as a distinct paradigm requiring innovative solutions, providing practical and theoretical insights for language preservation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches
Thakur, Madhavendra
Computation and Language
No-resource languages - those with minimal or no digital representation - pose unique challenges for machine translation (MT). Unlike low-resource languages, which rely on limited but existent corpora, no-resource languages often have fewer than 100 sentences available for training. This work explores the problem of no-resource translation through three distinct workflows: fine-tuning of translation-specific models, in-context learning with large language models (LLMs) using chain-of-reasoning prompting, and direct prompting without reasoning. Using Owens Valley Paiute as a case study, we demonstrate that no-resource translation demands fundamentally different approaches from low-resource scenarios, as traditional approaches to machine translation, such as those that work for low-resource languages, fail. Empirical results reveal that, although traditional approaches fail, the in-context learning capabilities of general-purpose large language models enable no-resource language translation that outperforms low-resource translation approaches and rivals human translations (BLEU 0.45-0.6); specifically, chain-of-reasoning prompting outperforms other methods for larger corpora, while direct prompting exhibits advantages in smaller datasets. As these approaches are language-agnostic, they have potential to be generalized to translation tasks from a wide variety of no-resource languages without expert input. These findings establish no-resource translation as a distinct paradigm requiring innovative solutions, providing practical and theoretical insights for language preservation.
title Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches
topic Computation and Language
url https://arxiv.org/abs/2412.20584