<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elsner-needle-2023-translating">
    <titleInfo>
        <title>Translating a low-resource language using GPT-3 and a human-readable dictionary</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Micha</namePart>
        <namePart type="family">Elsner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="family">Needle</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>Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Garrett</namePart>
            <namePart type="family">Nicolai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Eleanor</namePart>
            <namePart type="family">Chodroff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Frederic</namePart>
            <namePart type="family">Mailhot</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Çağrı</namePart>
            <namePart type="family">Çöltekin</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>We investigate how well words in the polysynthetic language Inuktitut can be translated by combining dictionary definitions, without use of a neural machine translation model trained on parallel text. Such a translation system would allow natural language technology to benefit from resources designed for community use in a language revitalization or education program, rather than requiring a separate parallel corpus. We show that the text-to-text generation capabilities of GPT-3 allow it to perform this task with BLEU scores of up to 18.5. We investigate prompting GPT-3 to provide multiple translations, which can help slightly, and providing it with grammar information, which is mostly ineffective. Finally, we test GPT-3’s ability to derive morpheme definitions from whole-word translations, but find this process is prone to errors including hallucinations.</abstract>
    <identifier type="citekey">elsner-needle-2023-translating</identifier>
    <identifier type="doi">10.18653/v1/2023.sigmorphon-1.2</identifier>
    <location>
        <url>https://aclanthology.org/2023.sigmorphon-1.2</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1</start>
            <end>13</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Translating a low-resource language using GPT-3 and a human-readable dictionary
%A Elsner, Micha
%A Needle, Jordan
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F elsner-needle-2023-translating
%X We investigate how well words in the polysynthetic language Inuktitut can be translated by combining dictionary definitions, without use of a neural machine translation model trained on parallel text. Such a translation system would allow natural language technology to benefit from resources designed for community use in a language revitalization or education program, rather than requiring a separate parallel corpus. We show that the text-to-text generation capabilities of GPT-3 allow it to perform this task with BLEU scores of up to 18.5. We investigate prompting GPT-3 to provide multiple translations, which can help slightly, and providing it with grammar information, which is mostly ineffective. Finally, we test GPT-3’s ability to derive morpheme definitions from whole-word translations, but find this process is prone to errors including hallucinations.
%R 10.18653/v1/2023.sigmorphon-1.2
%U https://aclanthology.org/2023.sigmorphon-1.2
%U https://doi.org/10.18653/v1/2023.sigmorphon-1.2
%P 1-13

Markdown (Informal)

[Translating a low-resource language using GPT-3 and a human-readable dictionary](https://aclanthology.org/2023.sigmorphon-1.2) (Elsner & Needle, SIGMORPHON 2023)

• Translating a low-resource language using GPT-3 and a human-readable dictionary (Elsner & Needle, SIGMORPHON 2023)

ACL

• Micha Elsner and Jordan Needle. 2023. Translating a low-resource language using GPT-3 and a human-readable dictionary. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 1–13, Toronto, Canada. Association for Computational Linguistics.