<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pupier-etal-2024-growing">
    <titleInfo>
        <title>Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adrien</namePart>
        <namePart type="family">Pupier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maximin</namePart>
        <namePart type="family">Coavoux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jérôme</namePart>
        <namePart type="family">Goulian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Lecouteux</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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Direct dependency parsing of the speech signal –as opposed to parsing speech transcriptions– has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser. In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing. We perform this evaluation on a large treebank of spoken French, featuring realistic spontaneous conversations. Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.</abstract>
    <identifier type="citekey">pupier-etal-2024-growing</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-short.22</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>225</start>
            <end>233</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech
%A Pupier, Adrien
%A Coavoux, Maximin
%A Goulian, Jérôme
%A Lecouteux, Benjamin
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F pupier-etal-2024-growing
%X Direct dependency parsing of the speech signal –as opposed to parsing speech transcriptions– has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser. In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing. We perform this evaluation on a large treebank of spoken French, featuring realistic spontaneous conversations. Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.
%U https://aclanthology.org/2024.acl-short.22
%P 225-233

Markdown (Informal)

[Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech](https://aclanthology.org/2024.acl-short.22) (Pupier et al., ACL 2024)

• Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech (Pupier et al., ACL 2024)

ACL

• Adrien Pupier, Maximin Coavoux, Jérôme Goulian, and Benjamin Lecouteux. 2024. Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 225–233, Bangkok, Thailand. Association for Computational Linguistics.