<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reheman-etal-2025-enhancing">
    <titleInfo>
        <title>Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abudurexiti</namePart>
        <namePart type="family">Reheman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junhao</namePart>
        <namePart type="family">Ruan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abudukeyumu</namePart>
        <namePart type="family">Abudula</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yingfeng</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tong</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">JingBo</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>Neural machine translation (NMT) has advanced significantly, yet challenges remain in adapting to new domains . In scenarios where bilingual data is limited, this issue is further exacerbated. To address this, we propose kNN-LM-NMT, a method that leverages semantically similar target language sentences in the kNN framework. Our approach generates a probability distribution over these sentences during decoding, and this distribution is then interpolated with the NMT model’s distribution. Additionally, we introduce an n-gram-based approach to focus on similar fragments, enabling the model to avoid the noise introduced by the non-similar parts. To enhance accuracy, we further incorporate cross-lingual retrieval similarity to refine the kNN probability distribution. Extensive experiments on multi-domain datasets demonstrate significant performance improvements in both high-resource and low-resource scenarios. Our approach effectively extracts translation knowledge from limited target domain data, and well benefits from large-scale monolingual data for robust context representation.</abstract>
    <identifier type="citekey">reheman-etal-2025-enhancing</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.496</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.496/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>10053</start>
            <end>10065</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation
%A Reheman, Abudurexiti
%A Liu, Hongyu
%A Ruan, Junhao
%A Abudula, Abudukeyumu
%A Luo, Yingfeng
%A Xiao, Tong
%A Zhu, JingBo
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F reheman-etal-2025-enhancing
%X Neural machine translation (NMT) has advanced significantly, yet challenges remain in adapting to new domains . In scenarios where bilingual data is limited, this issue is further exacerbated. To address this, we propose kNN-LM-NMT, a method that leverages semantically similar target language sentences in the kNN framework. Our approach generates a probability distribution over these sentences during decoding, and this distribution is then interpolated with the NMT model’s distribution. Additionally, we introduce an n-gram-based approach to focus on similar fragments, enabling the model to avoid the noise introduced by the non-similar parts. To enhance accuracy, we further incorporate cross-lingual retrieval similarity to refine the kNN probability distribution. Extensive experiments on multi-domain datasets demonstrate significant performance improvements in both high-resource and low-resource scenarios. Our approach effectively extracts translation knowledge from limited target domain data, and well benefits from large-scale monolingual data for robust context representation.
%R 10.18653/v1/2025.acl-long.496
%U https://aclanthology.org/2025.acl-long.496/
%U https://doi.org/10.18653/v1/2025.acl-long.496
%P 10053-10065

Markdown (Informal)

[Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation](https://aclanthology.org/2025.acl-long.496/) (Reheman et al., ACL 2025)

• Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation (Reheman et al., ACL 2025)

ACL

• Abudurexiti Reheman, Hongyu Liu, Junhao Ruan, Abudukeyumu Abudula, Yingfeng Luo, Tong Xiao, and JingBo Zhu. 2025. Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10053–10065, Vienna, Austria. Association for Computational Linguistics.