<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mavromatis-etal-2026-ancient">
    <titleInfo>
        <title>Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Spyridon</namePart>
        <namePart type="family">Mavromatis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sokratis</namePart>
        <namePart type="family">Sofianopoulos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Prokopis</namePart>
        <namePart type="family">Prokopidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Giagkou</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>Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this gap by introducing the AG-MG Parallel Corpus, a new resource containing 132,481 sentence-aligned pairs derived from literary, historical, and biblical texts. We present a novel corpus creation pipeline that combines web-scraped, excerpt-level data with a multi-stage sentence-level alignment, and refinement process. Our method uses VecAlign with LaBSE embeddings, which we first fine-tune on a manually-aligned AG-MG subset, followed by an LLM-based error/misalignment correction phase using Gemini 2.5 Flash to ensure high alignment quality. Furthermore, we provide the first comprehensive benchmark of modern MT models on this task, evaluating three fine-tuning strategies across NMT models (NLLB, M2M100) and a Greek LLM (Llama-Krikri-8B). Our experiments show that fine-tuning yields significant improvements over base models, increasing performance by up to +10.3 BLEU points. Specifically, full-parameter fine-tuning of Llama-Krikri-8B achieves the highest overall performance with a BLEU score of 13.16, while the QLoRA-adapted M2M100-1.2B model demonstrates the largest relative gains and highly competitive results. Our dataset and models represent a significant contribution to Greek NLP.</abstract>
    <identifier type="citekey">mavromatis-etal-2026-ancient</identifier>
    <identifier type="doi">10.63317/4cdk64dgm2w9</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.684/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>8685</start>
            <end>8698</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models
%A Mavromatis, Spyridon
%A Sofianopoulos, Sokratis
%A Prokopidis, Prokopis
%A Giagkou, Maria
%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 mavromatis-etal-2026-ancient
%X Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this gap by introducing the AG-MG Parallel Corpus, a new resource containing 132,481 sentence-aligned pairs derived from literary, historical, and biblical texts. We present a novel corpus creation pipeline that combines web-scraped, excerpt-level data with a multi-stage sentence-level alignment, and refinement process. Our method uses VecAlign with LaBSE embeddings, which we first fine-tune on a manually-aligned AG-MG subset, followed by an LLM-based error/misalignment correction phase using Gemini 2.5 Flash to ensure high alignment quality. Furthermore, we provide the first comprehensive benchmark of modern MT models on this task, evaluating three fine-tuning strategies across NMT models (NLLB, M2M100) and a Greek LLM (Llama-Krikri-8B). Our experiments show that fine-tuning yields significant improvements over base models, increasing performance by up to +10.3 BLEU points. Specifically, full-parameter fine-tuning of Llama-Krikri-8B achieves the highest overall performance with a BLEU score of 13.16, while the QLoRA-adapted M2M100-1.2B model demonstrates the largest relative gains and highly competitive results. Our dataset and models represent a significant contribution to Greek NLP.
%R 10.63317/4cdk64dgm2w9
%U https://aclanthology.org/2026.lrec-1.684/
%U https://doi.org/10.63317/4cdk64dgm2w9
%P 8685-8698

Markdown (Informal)

[Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models](https://aclanthology.org/2026.lrec-1.684/) (Mavromatis et al., LREC 2026)

• Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models (Mavromatis et al., LREC 2026)

ACL

• Spyridon Mavromatis, Sokratis Sofianopoulos, Prokopis Prokopidis, and Maria Giagkou. 2026. Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 8685–8698, Palma de Mallorca, Spain. ELRA Language Resource Association.