<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jwalapuram-2023-pulling">
    <titleInfo>
        <title>Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Prathyusha</namePart>
        <namePart type="family">Jwalapuram</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Much of the work testing machine translation systems for robustness and sensitivity has been adversarial or tended towards testing noisy input such as spelling errors, or non-standard input such as dialects. In this work, we take a step back to investigate a sensitivity problem that can seem trivial and is often overlooked: punctuation. We perform basic sentence-final insertion and deletion perturbation tests with full stops, exclamation and questions marks across source languages and demonstrate a concerning finding: commercial, production-level machine translation systems are vulnerable to mere single punctuation insertion or deletion, resulting in unreliable translations. Moreover, we demonstrate that both string-based and model-based evaluation metrics also suffer from this vulnerability, producing significantly different scores when translations only differ in a single punctuation, with model-based metrics penalizing each punctuation differently. Our work calls into question the reliability of machine translation systems and their evaluation metrics, particularly for real-world use cases, where inconsistent punctuation is often the most common and the least disruptive noise.</abstract>
    <identifier type="citekey">jwalapuram-2023-pulling</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.381</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.381</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>6116</start>
            <end>6130</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation
%A Jwalapuram, Prathyusha
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F jwalapuram-2023-pulling
%X Much of the work testing machine translation systems for robustness and sensitivity has been adversarial or tended towards testing noisy input such as spelling errors, or non-standard input such as dialects. In this work, we take a step back to investigate a sensitivity problem that can seem trivial and is often overlooked: punctuation. We perform basic sentence-final insertion and deletion perturbation tests with full stops, exclamation and questions marks across source languages and demonstrate a concerning finding: commercial, production-level machine translation systems are vulnerable to mere single punctuation insertion or deletion, resulting in unreliable translations. Moreover, we demonstrate that both string-based and model-based evaluation metrics also suffer from this vulnerability, producing significantly different scores when translations only differ in a single punctuation, with model-based metrics penalizing each punctuation differently. Our work calls into question the reliability of machine translation systems and their evaluation metrics, particularly for real-world use cases, where inconsistent punctuation is often the most common and the least disruptive noise.
%R 10.18653/v1/2023.findings-acl.381
%U https://aclanthology.org/2023.findings-acl.381
%U https://doi.org/10.18653/v1/2023.findings-acl.381
%P 6116-6130

Markdown (Informal)

[Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation](https://aclanthology.org/2023.findings-acl.381) (Jwalapuram, Findings 2023)

• Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation (Jwalapuram, Findings 2023)

ACL

• Prathyusha Jwalapuram. 2023. Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6116–6130, Toronto, Canada. Association for Computational Linguistics.