<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-nguyen-2022-investigating">
    <titleInfo>
        <title>Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Linh</namePart>
        <namePart type="given">The</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dat</namePart>
        <namePart type="given">Quoc</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop On Transcript Understanding</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Franck</namePart>
            <namePart type="family">Dernoncourt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thien</namePart>
            <namePart type="given">Huu</namePart>
            <namePart type="family">Nguyen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viet</namePart>
            <namePart type="given">Dac</namePart>
            <namePart type="family">Lai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amir</namePart>
            <namePart type="given">Pouran</namePart>
            <namePart type="given">Ben</namePart>
            <namePart type="family">Veyseh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trung</namePart>
            <namePart type="given">H</namePart>
            <namePart type="family">Bui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="given">Seunghyun</namePart>
            <namePart type="family">Yoon</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Conference on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, South Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present an empirical study investigating the influence of automatic speech recognition (ASR) errors on the spoken implicit discourse relation recognition (IDRR) task. We construct a spoken dataset for this task based on the Penn Discourse Treebank 2.0. On this dataset, we conduct “Cascaded” experiments employing state-of-the-art ASR and text-based IDRR models and find that the ASR errors significantly decrease the IDRR performance. In addition, the “Cascaded” approach does remarkably better than an “End-to-End” one that directly predicts a relation label for each input argument speech pair.</abstract>
    <identifier type="citekey">nguyen-nguyen-2022-investigating</identifier>
    <location>
        <url>https://aclanthology.org/2022.tu-1.5/</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>34</start>
            <end>39</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition
%A Nguyen, Linh The
%A Nguyen, Dat Quoc
%Y Dernoncourt, Franck
%Y Nguyen, Thien Huu
%Y Lai, Viet Dac
%Y Veyseh, Amir Pouran Ben
%Y Bui, Trung H.
%Y Yoon, David Seunghyun
%S Proceedings of the First Workshop On Transcript Understanding
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, South Korea
%F nguyen-nguyen-2022-investigating
%X We present an empirical study investigating the influence of automatic speech recognition (ASR) errors on the spoken implicit discourse relation recognition (IDRR) task. We construct a spoken dataset for this task based on the Penn Discourse Treebank 2.0. On this dataset, we conduct “Cascaded” experiments employing state-of-the-art ASR and text-based IDRR models and find that the ASR errors significantly decrease the IDRR performance. In addition, the “Cascaded” approach does remarkably better than an “End-to-End” one that directly predicts a relation label for each input argument speech pair.
%U https://aclanthology.org/2022.tu-1.5/
%P 34-39

Markdown (Informal)

[Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition](https://aclanthology.org/2022.tu-1.5/) (Nguyen & Nguyen, TU 2022)

• Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition (Nguyen & Nguyen, TU 2022)

ACL

• Linh The Nguyen and Dat Quoc Nguyen. 2022. Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition. In Proceedings of the First Workshop On Transcript Understanding, pages 34–39, Gyeongju, South Korea. International Conference on Computational Linguistics.