<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gain-etal-2023-reference">
    <titleInfo>
        <title>Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Baban</namePart>
        <namePart type="family">Gain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ramakrishna</namePart>
        <namePart type="family">Appicharla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soumya</namePart>
        <namePart type="family">Chennabasavaraj</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikesh</namePart>
        <namePart type="family">Garera</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Asif</namePart>
        <namePart type="family">Ekbal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muthusamy</namePart>
        <namePart type="family">Chelliah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Community Question-Answering (CQA) portals serve as a valuable tool for helping users within an organization. However, making them accessible to non-English-speaking users continues to be a challenge. Translating questions can broaden the community’s reach, benefiting individuals with similar inquiries in various languages. Translating questions using Neural Machine Translation (NMT) poses more challenges, especially in noisy environments, where the grammatical correctness of the questions is not monitored. These questions may be phrased as statements by non-native speakers, with incorrect subject-verb order and sometimes even missing question marks. Creating a synthetic parallel corpus from such data is also difficult due to its noisy nature. To address this issue, we propose a training methodology that fine-tunes the NMT system only using source-side data. Our approach balances adequacy and fluency by utilizing a loss function that combines BERTScore and Masked Language Model (MLM) Score. Our method surpasses the conventional Maximum Likelihood Estimation (MLE) based fine-tuning approach, which relies on synthetic target data, by achieving a 1.9 BLEU score improvement. Our model exhibits robustness while we add noise to our baseline, and still achieve 1.1 BLEU improvement and large improvements on TER and BLEURT metrics. Our proposed methodology is model-agnostic and is only necessary during the training phase. We make the codes and datasets publicly available at https://www.iitp.ac.in/ ai-nlp-ml/resources.html#DomainAdapt for facilitating further research.</abstract>
    <identifier type="citekey">gain-etal-2023-reference</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.16</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.16</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>207</start>
            <end>221</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards
%A Gain, Baban
%A Appicharla, Ramakrishna
%A Chennabasavaraj, Soumya
%A Garera, Nikesh
%A Ekbal, Asif
%A Chelliah, Muthusamy
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F gain-etal-2023-reference
%X Community Question-Answering (CQA) portals serve as a valuable tool for helping users within an organization. However, making them accessible to non-English-speaking users continues to be a challenge. Translating questions can broaden the community’s reach, benefiting individuals with similar inquiries in various languages. Translating questions using Neural Machine Translation (NMT) poses more challenges, especially in noisy environments, where the grammatical correctness of the questions is not monitored. These questions may be phrased as statements by non-native speakers, with incorrect subject-verb order and sometimes even missing question marks. Creating a synthetic parallel corpus from such data is also difficult due to its noisy nature. To address this issue, we propose a training methodology that fine-tunes the NMT system only using source-side data. Our approach balances adequacy and fluency by utilizing a loss function that combines BERTScore and Masked Language Model (MLM) Score. Our method surpasses the conventional Maximum Likelihood Estimation (MLE) based fine-tuning approach, which relies on synthetic target data, by achieving a 1.9 BLEU score improvement. Our model exhibits robustness while we add noise to our baseline, and still achieve 1.1 BLEU improvement and large improvements on TER and BLEURT metrics. Our proposed methodology is model-agnostic and is only necessary during the training phase. We make the codes and datasets publicly available at https://www.iitp.ac.in/ ai-nlp-ml/resources.html#DomainAdapt for facilitating further research.
%R 10.18653/v1/2023.findings-emnlp.16
%U https://aclanthology.org/2023.findings-emnlp.16
%U https://doi.org/10.18653/v1/2023.findings-emnlp.16
%P 207-221

Markdown (Informal)

[Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards](https://aclanthology.org/2023.findings-emnlp.16) (Gain et al., Findings 2023)

• Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards (Gain et al., Findings 2023)

ACL

• Baban Gain, Ramakrishna Appicharla, Soumya Chennabasavaraj, Nikesh Garera, Asif Ekbal, and Muthusamy Chelliah. 2023. Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 207–221, Singapore. Association for Computational Linguistics.