<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sia-duh-2023-context">
    <titleInfo>
        <title>In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Suzanna</namePart>
        <namePart type="family">Sia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Duh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Masao</namePart>
            <namePart type="family">Utiyama</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Asia-Pacific Association for Machine Translation</publisher>
            <place>
                <placeTerm type="text">Macau SAR, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The phenomena of in-context learning has typically been thought of as “learning from examples”. In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining coherency with its context, i.e., the prompt examples. We first investigate randomly sampled prompts across 4 domains, and find that translation performance improves when shown in-domain prompts. Next, we investigate coherency for the in-domain setting, which uses prompt examples from a moving window. We study this with respect to other factors that have previously been identified in the literature such as length, surface similarity and sentence embedding similarity. Our results across 3 models (GPTNeo2.7B, Bloom3B, XGLM2.9B), and three translation directions (en\rightarrowpt, de, fr) suggest that the long-term coherency of the prompts and the test sentence is a good indicator of downstream translation performance. In doing so, we demonstrate the efficacy of in-context Machine Translation for on-the-fly adaptation.</abstract>
    <identifier type="citekey">sia-duh-2023-context</identifier>
    <location>
        <url>https://aclanthology.org/2023.mtsummit-research.15</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>173</start>
            <end>185</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models
%A Sia, Suzanna
%A Duh, Kevin
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F sia-duh-2023-context
%X The phenomena of in-context learning has typically been thought of as “learning from examples”. In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining coherency with its context, i.e., the prompt examples. We first investigate randomly sampled prompts across 4 domains, and find that translation performance improves when shown in-domain prompts. Next, we investigate coherency for the in-domain setting, which uses prompt examples from a moving window. We study this with respect to other factors that have previously been identified in the literature such as length, surface similarity and sentence embedding similarity. Our results across 3 models (GPTNeo2.7B, Bloom3B, XGLM2.9B), and three translation directions (en\rightarrowpt, de, fr) suggest that the long-term coherency of the prompts and the test sentence is a good indicator of downstream translation performance. In doing so, we demonstrate the efficacy of in-context Machine Translation for on-the-fly adaptation.
%U https://aclanthology.org/2023.mtsummit-research.15
%P 173-185

Markdown (Informal)

[In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models](https://aclanthology.org/2023.mtsummit-research.15) (Sia & Duh, MTSummit 2023)

• In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models (Sia & Duh, MTSummit 2023)

ACL

• Suzanna Sia and Kevin Duh. 2023. In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 173–185, Macau SAR, China. Asia-Pacific Association for Machine Translation.