From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation

Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, Katharina von der Wense
12/1/2024
cs.CLcs.LG

No official code found. Best implementation: alimarashian/da_lr_nmt (2 stars, MIT, last commit 2025-05-25).

Abstract

Many of the world's languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only available parallel data are small amounts of religious texts. Hence, domain adaptation (DA) is a crucial issue faced by contemporary NMT and has, so far, been underexplored for low-resource languages. In this paper, we evaluate a set of methods from both low-resource NMT and DA in a realistic setting, in which we aim to translate between a high-resource and a low-resource language with access to only: a) parallel Bible data, b) a bilingual dictionary, and c) a monolingual target-domain corpus in the high-resource language. Our results show that the effectiveness of the tested methods varies, with the simplest one, DALI, being most effective. We follow up with a small human evaluation of DALI, which shows that there is still a need for more careful investigation of how to accomplish DA for low-resource NMT.

View on arXivView PDF

Code Implementations(1)

alimarashian/da_lr_nmtCommunity100%
MIT

This is the repository containing the implementation details for the COLING 2025 paper "From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation"

20Lex, TclDec 16, 20241 years agoMIT

Similar Papers

Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG

87% match2026

Enhancing Neural Machine Translation of Low-Resource Languages: Corpus Development, Human Evaluation and Explainable AI Architectures

85% match2024

Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation

85% match2025

TULUN: Transparent and Adaptable Low-resource Machine Translation

84% match1 repo52025

Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation

84% match2024

Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study

84% match1 repo52024

Cite this paper

@article{marashian2024from,
  title  = {From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation},
  author = {Ali Marashian and Enora Rice and Luke Gessler and Alexis Palmer and Katharina von der Wense},
  year   = {2024},
  eprint = {2412.00966},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.00966v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.00966.svg)](https://codeofpaper.com/paper/2412.00966)

Discussion