<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="denisov-vu-2024-teaching">
    <titleInfo>
        <title>Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pavel</namePart>
        <namePart type="family">Denisov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thang</namePart>
        <namePart type="family">Vu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent advancements in language modeling have led to the emergenceof Large Language Models (LLMs) capable ofvarious natural language processing tasks.Despite their success in text-based tasks, applying LLMs to the speech domainremains limited and challenging. This paper presents BLOOMZMMS, a novel modelthat integrates a multilingual LLM with a multilingual speech encoder,aiming to harness the capabilities of LLMs for speech recognition and beyond.Utilizing a multi-instructional training approach, we demonstrate the transferabilityof linguistic knowledge from the text to the speech modality.Our experiments, conducted on 1900 hours of transcribed data from 139 languages,establish that a multilingual speech representation can be effectivelylearned and aligned with a multilingual LLM. While this learned representationinitially shows limitations in task generalization, we address this issue bygenerating synthetic targets in a multi-instructional style.Our zero-shot evaluation results confirm the robustness of our approach acrossmultiple tasks, including speech translation and multilingual spoken languageunderstanding, thereby opening new avenues for applying LLMs in the speech domain.</abstract>
    <identifier type="citekey">denisov-vu-2024-teaching</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.52</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>814</start>
            <end>834</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training
%A Denisov, Pavel
%A Vu, Thang
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F denisov-vu-2024-teaching
%X Recent advancements in language modeling have led to the emergenceof Large Language Models (LLMs) capable ofvarious natural language processing tasks.Despite their success in text-based tasks, applying LLMs to the speech domainremains limited and challenging. This paper presents BLOOMZMMS, a novel modelthat integrates a multilingual LLM with a multilingual speech encoder,aiming to harness the capabilities of LLMs for speech recognition and beyond.Utilizing a multi-instructional training approach, we demonstrate the transferabilityof linguistic knowledge from the text to the speech modality.Our experiments, conducted on 1900 hours of transcribed data from 139 languages,establish that a multilingual speech representation can be effectivelylearned and aligned with a multilingual LLM. While this learned representationinitially shows limitations in task generalization, we address this issue bygenerating synthetic targets in a multi-instructional style.Our zero-shot evaluation results confirm the robustness of our approach acrossmultiple tasks, including speech translation and multilingual spoken languageunderstanding, thereby opening new avenues for applying LLMs in the speech domain.
%U https://aclanthology.org/2024.findings-naacl.52
%P 814-834

Markdown (Informal)

[Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training](https://aclanthology.org/2024.findings-naacl.52) (Denisov & Vu, Findings 2024)

• Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training (Denisov & Vu, Findings 2024)

ACL

• Pavel Denisov and Thang Vu. 2024. Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 814–834, Mexico City, Mexico. Association for Computational Linguistics.