<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="regmi-etal-2026-nepali">
    <titleInfo>
        <title>Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sunil</namePart>
        <namePart type="family">Regmi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sundeep</namePart>
        <namePart type="family">Dawadi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bal</namePart>
        <namePart type="given">Krishna</namePart>
        <namePart type="family">Bal</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>The Nepali language has a rich and complex morphology. Existing lemmatization research focuses on traditional rule-based or TRIE-based approaches. These methods often fail when encountering out-of-vocabulary or misspelled words. This paper investigates neural lemmatization for the under-resourced Nepali language using multilingual transformer models. We formulate lemmatization as a text-to-text generation problem and evaluate its impacts on downstream tasks by finetuning mBART-large-50, mT5-base, and mT5-small. The models were trained on a combination of publicly available and human-annotated word-lemma pair (8,000 instances) dataset. The performance is evaluated using Character Error Rate (CER), accuracy, character-level Bilingual Evaluation Understudy (BLEU), and morphological coverage. The mT5-base model achieved the highest overall performance. The model achieved 96.1% accuracy and a 1.1% CER using a learning rate of 5 × 10\ensuremath-4. However, it showed slightly weaker performance in handling complex morphological variations. The mBART-large-50 model followed closely with 96.0% accuracy and 0.970 morphological coverage. To assess the efficacy of these models, we applied lemmatization to downstream tasks. In Hindi-Nepali cross-lingual alignment, performance improved significantly from 12.86% to 41.61% using mBART model. In information retrieval, the Mean Average Precision (MAP)@1 using binary index increased from 0.71 to 0.90 using mBART model. These results demonstrate that multilingual transformers effectively learn morphological transformations for low-resource languages through text-to-text generation.</abstract>
    <identifier type="citekey">regmi-etal-2026-nepali</identifier>
    <identifier type="doi">10.63317/2o6euz7qakr5</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.275/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>3462</start>
            <end>3469</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting
%A Regmi, Sunil
%A Dawadi, Sundeep
%A Bal, Bal Krishna
%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 regmi-etal-2026-nepali
%X The Nepali language has a rich and complex morphology. Existing lemmatization research focuses on traditional rule-based or TRIE-based approaches. These methods often fail when encountering out-of-vocabulary or misspelled words. This paper investigates neural lemmatization for the under-resourced Nepali language using multilingual transformer models. We formulate lemmatization as a text-to-text generation problem and evaluate its impacts on downstream tasks by finetuning mBART-large-50, mT5-base, and mT5-small. The models were trained on a combination of publicly available and human-annotated word-lemma pair (8,000 instances) dataset. The performance is evaluated using Character Error Rate (CER), accuracy, character-level Bilingual Evaluation Understudy (BLEU), and morphological coverage. The mT5-base model achieved the highest overall performance. The model achieved 96.1% accuracy and a 1.1% CER using a learning rate of 5 × 10\ensuremath-4. However, it showed slightly weaker performance in handling complex morphological variations. The mBART-large-50 model followed closely with 96.0% accuracy and 0.970 morphological coverage. To assess the efficacy of these models, we applied lemmatization to downstream tasks. In Hindi-Nepali cross-lingual alignment, performance improved significantly from 12.86% to 41.61% using mBART model. In information retrieval, the Mean Average Precision (MAP)@1 using binary index increased from 0.71 to 0.90 using mBART model. These results demonstrate that multilingual transformers effectively learn morphological transformations for low-resource languages through text-to-text generation.
%R 10.63317/2o6euz7qakr5
%U https://aclanthology.org/2026.lrec-1.275/
%U https://doi.org/10.63317/2o6euz7qakr5
%P 3462-3469

Markdown (Informal)

[Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting](https://aclanthology.org/2026.lrec-1.275/) (Regmi et al., LREC 2026)

• Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting (Regmi et al., LREC 2026)

ACL

• Sunil Regmi, Sundeep Dawadi, and Bal Krishna Bal. 2026. Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3462–3469, Palma de Mallorca, Spain. ELRA Language Resource Association.