@inproceedings{mcgiff-nikolov-2026-semiadapt,
title = "{S}emi{A}dapt: Semi-Supervised and Efficient {L}o{RA}-Based Domain Adaptation for Low-Resource {I}rish Machine Translation with Transformers",
author = "Mcgiff, Josh and
Nikolov, Nikola S.",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.801/",
doi = "10.63317/2gfkah2nq6uv",
pages = "10208--10220",
abstract = "Fine-tuning is widely used to adapt multilingual Transformer models for machine translation (MT) in specific domains. However, full-parameter fine-tuning of large multilingual models with billions of parameters is computationally expensive, thus creating a barrier to entry for researchers working on low-resource tasks such as Irish translation. Parameter-efficient fine-tuning (PEFT) addresses this by updating a fraction of the original model parameters, with the Low-Rank Adaptation approach (LoRA) introducing small, trainable adapter layers. We introduce SemiAdapt-Full and SemiAdapt-LoRA as semi-supervised approaches that leverage inferred domains to improve overall performance in MT. SemiAdapt-LoRA employs dynamic routing at inference time, eliminating the need to load multiple separately fine-tuned models. Instead, a single shared base model is maintained while lightweight domain-specific adapters, updating only 1.39{\%} of the model parameters in our case, are activated dynamically. We demonstrate that SemiAdapt-Full can outperform full-model fine-tuning and SemiAdapt-LoRA can propel PEFT methods to compete with full-model fine-tuning. We further evaluate corpus-level domain fine-tuning and demonstrate that our embedding-based inference methods perform especially well on larger and noisier corpora. Code and training configurations are released to support reproducibility. Ultimately, our approach narrows the performance gap between PEFT and full-parameter fine-tuning, offering resource-constrained researchers a computationally efficient alternative."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcgiff-nikolov-2026-semiadapt">
<titleInfo>
<title>SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Mcgiff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Nikolov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-tuning is widely used to adapt multilingual Transformer models for machine translation (MT) in specific domains. However, full-parameter fine-tuning of large multilingual models with billions of parameters is computationally expensive, thus creating a barrier to entry for researchers working on low-resource tasks such as Irish translation. Parameter-efficient fine-tuning (PEFT) addresses this by updating a fraction of the original model parameters, with the Low-Rank Adaptation approach (LoRA) introducing small, trainable adapter layers. We introduce SemiAdapt-Full and SemiAdapt-LoRA as semi-supervised approaches that leverage inferred domains to improve overall performance in MT. SemiAdapt-LoRA employs dynamic routing at inference time, eliminating the need to load multiple separately fine-tuned models. Instead, a single shared base model is maintained while lightweight domain-specific adapters, updating only 1.39% of the model parameters in our case, are activated dynamically. We demonstrate that SemiAdapt-Full can outperform full-model fine-tuning and SemiAdapt-LoRA can propel PEFT methods to compete with full-model fine-tuning. We further evaluate corpus-level domain fine-tuning and demonstrate that our embedding-based inference methods perform especially well on larger and noisier corpora. Code and training configurations are released to support reproducibility. Ultimately, our approach narrows the performance gap between PEFT and full-parameter fine-tuning, offering resource-constrained researchers a computationally efficient alternative.</abstract>
<identifier type="citekey">mcgiff-nikolov-2026-semiadapt</identifier>
<identifier type="doi">10.63317/2gfkah2nq6uv</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.801/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10208</start>
<end>10220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers
%A Mcgiff, Josh
%A Nikolov, Nikola S.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F mcgiff-nikolov-2026-semiadapt
%X Fine-tuning is widely used to adapt multilingual Transformer models for machine translation (MT) in specific domains. However, full-parameter fine-tuning of large multilingual models with billions of parameters is computationally expensive, thus creating a barrier to entry for researchers working on low-resource tasks such as Irish translation. Parameter-efficient fine-tuning (PEFT) addresses this by updating a fraction of the original model parameters, with the Low-Rank Adaptation approach (LoRA) introducing small, trainable adapter layers. We introduce SemiAdapt-Full and SemiAdapt-LoRA as semi-supervised approaches that leverage inferred domains to improve overall performance in MT. SemiAdapt-LoRA employs dynamic routing at inference time, eliminating the need to load multiple separately fine-tuned models. Instead, a single shared base model is maintained while lightweight domain-specific adapters, updating only 1.39% of the model parameters in our case, are activated dynamically. We demonstrate that SemiAdapt-Full can outperform full-model fine-tuning and SemiAdapt-LoRA can propel PEFT methods to compete with full-model fine-tuning. We further evaluate corpus-level domain fine-tuning and demonstrate that our embedding-based inference methods perform especially well on larger and noisier corpora. Code and training configurations are released to support reproducibility. Ultimately, our approach narrows the performance gap between PEFT and full-parameter fine-tuning, offering resource-constrained researchers a computationally efficient alternative.
%R 10.63317/2gfkah2nq6uv
%U https://aclanthology.org/2026.lrec-1.801/
%U https://doi.org/10.63317/2gfkah2nq6uv
%P 10208-10220
Markdown (Informal)
[SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers](https://aclanthology.org/2026.lrec-1.801/) (Mcgiff & Nikolov, LREC 2026)
ACL