<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brazier-rouas-2024-conditioning">
    <titleInfo>
        <title>Conditioning LLMs with Emotion in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Charles</namePart>
        <namePart type="family">Brazier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Luc</namePart>
        <namePart type="family">Rouas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) have shown remarkable performance in Natural Language Processing tasks, including Machine Translation (MT). In this work, we propose a novel MT pipeline that integrates emotion information extracted from a Speech Emotion Recognition (SER) model into LLMs to enhance translation quality. We first fine-tune five existing LLMs on the Libri-trans dataset and select the most performant model. Subsequently, we augment LLM prompts with different dimensional emotions and train the selected LLM under these different configurations. Our experiments reveal that integrating emotion information, especially arousal, into LLM prompts leads to notable improvements in translation quality.</abstract>
    <identifier type="citekey">brazier-rouas-2024-conditioning</identifier>
    <location>
        <url>https://aclanthology.org/2024.iwslt-1.5</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>33</start>
            <end>38</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Conditioning LLMs with Emotion in Neural Machine Translation
%A Brazier, Charles
%A Rouas, Jean-Luc
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F brazier-rouas-2024-conditioning
%X Large Language Models (LLMs) have shown remarkable performance in Natural Language Processing tasks, including Machine Translation (MT). In this work, we propose a novel MT pipeline that integrates emotion information extracted from a Speech Emotion Recognition (SER) model into LLMs to enhance translation quality. We first fine-tune five existing LLMs on the Libri-trans dataset and select the most performant model. Subsequently, we augment LLM prompts with different dimensional emotions and train the selected LLM under these different configurations. Our experiments reveal that integrating emotion information, especially arousal, into LLM prompts leads to notable improvements in translation quality.
%U https://aclanthology.org/2024.iwslt-1.5
%P 33-38

Markdown (Informal)

[Conditioning LLMs with Emotion in Neural Machine Translation](https://aclanthology.org/2024.iwslt-1.5) (Brazier & Rouas, IWSLT 2024)

• Conditioning LLMs with Emotion in Neural Machine Translation (Brazier & Rouas, IWSLT 2024)

ACL

• Charles Brazier and Jean-Luc Rouas. 2024. Conditioning LLMs with Emotion in Neural Machine Translation. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 33–38, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.