<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="renduchintala-williams-2022-investigating">
    <titleInfo>
        <title>Investigating Failures of Automatic Translationin the Case of Unambiguous Gender</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adithya</namePart>
        <namePart type="family">Renduchintala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adina</namePart>
        <namePart type="family">Williams</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer-based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by current state-of-the-art NMT models with regards to translating from a language that doesn’t mark gender on nouns into others that do. We find that even when the surrounding context provides unambiguous evidence of the appropriate grammatical gender marking, no tested model was able to accurately gender occupation nouns systematically. We release an evaluation scheme and dataset for measuring the ability of NMT models to translate gender morphology correctly in unambiguous contexts across syntactically diverse sentences. Our dataset translates from an English source into 20 languages from several different language families. With the availability of this dataset, our hope is that the NMT community can iterate on solutions for this class of especially egregious errors.</abstract>
    <identifier type="citekey">renduchintala-williams-2022-investigating</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-long.243</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-long.243</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>3454</start>
            <end>3469</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating Failures of Automatic Translationin the Case of Unambiguous Gender
%A Renduchintala, Adithya
%A Williams, Adina
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F renduchintala-williams-2022-investigating
%X Transformer-based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by current state-of-the-art NMT models with regards to translating from a language that doesn’t mark gender on nouns into others that do. We find that even when the surrounding context provides unambiguous evidence of the appropriate grammatical gender marking, no tested model was able to accurately gender occupation nouns systematically. We release an evaluation scheme and dataset for measuring the ability of NMT models to translate gender morphology correctly in unambiguous contexts across syntactically diverse sentences. Our dataset translates from an English source into 20 languages from several different language families. With the availability of this dataset, our hope is that the NMT community can iterate on solutions for this class of especially egregious errors.
%R 10.18653/v1/2022.acl-long.243
%U https://aclanthology.org/2022.acl-long.243
%U https://doi.org/10.18653/v1/2022.acl-long.243
%P 3454-3469

Markdown (Informal)

[Investigating Failures of Automatic Translationin the Case of Unambiguous Gender](https://aclanthology.org/2022.acl-long.243) (Renduchintala & Williams, ACL 2022)

• Investigating Failures of Automatic Translationin the Case of Unambiguous Gender (Renduchintala & Williams, ACL 2022)

ACL

• Adithya Renduchintala and Adina Williams. 2022. Investigating Failures of Automatic Translationin the Case of Unambiguous Gender. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3454–3469, Dublin, Ireland. Association for Computational Linguistics.