@inproceedings{culnan-etal-2021-ire,
title = "Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection",
author = "Culnan, John and
Park, Seongjin and
Krishnaswamy, Meghavarshini and
Sharp, Rebecca",
editor = "De Clercq, Orphee and
Balahur, Alexandra and
Sedoc, Joao and
Barriere, Valentin and
Tafreshi, Shabnam and
Buechel, Sven and
Hoste, Veronique",
booktitle = "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wassa-1.26",
pages = "250--256",
abstract = "In deployment, systems that use speech as input must make use of automated transcriptions. Yet, typically when these systems are evaluated, gold transcriptions are assumed. We explicitly examine the impact of transcription errors on the downstream performance of a multi-modal system on three related tasks from three datasets: emotion, sarcasm, and personality detection. We include three separate transcription tools and show that while all automated transcriptions propagate errors that substantially impact downstream performance, the open-source tools fair worse than the paid tool, though not always straightforwardly, and word error rates do not correlate well with downstream performance. We further find that the inclusion of audio features partially mitigates transcription errors, but that a naive usage of a multi-task setup does not.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="culnan-etal-2021-ire">
<titleInfo>
<title>Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Culnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongjin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghavarshini</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Buechel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In deployment, systems that use speech as input must make use of automated transcriptions. Yet, typically when these systems are evaluated, gold transcriptions are assumed. We explicitly examine the impact of transcription errors on the downstream performance of a multi-modal system on three related tasks from three datasets: emotion, sarcasm, and personality detection. We include three separate transcription tools and show that while all automated transcriptions propagate errors that substantially impact downstream performance, the open-source tools fair worse than the paid tool, though not always straightforwardly, and word error rates do not correlate well with downstream performance. We further find that the inclusion of audio features partially mitigates transcription errors, but that a naive usage of a multi-task setup does not.</abstract>
<identifier type="citekey">culnan-etal-2021-ire</identifier>
<location>
<url>https://aclanthology.org/2021.wassa-1.26</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>250</start>
<end>256</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection
%A Culnan, John
%A Park, Seongjin
%A Krishnaswamy, Meghavarshini
%A Sharp, Rebecca
%Y De Clercq, Orphee
%Y Balahur, Alexandra
%Y Sedoc, Joao
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Buechel, Sven
%Y Hoste, Veronique
%S Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F culnan-etal-2021-ire
%X In deployment, systems that use speech as input must make use of automated transcriptions. Yet, typically when these systems are evaluated, gold transcriptions are assumed. We explicitly examine the impact of transcription errors on the downstream performance of a multi-modal system on three related tasks from three datasets: emotion, sarcasm, and personality detection. We include three separate transcription tools and show that while all automated transcriptions propagate errors that substantially impact downstream performance, the open-source tools fair worse than the paid tool, though not always straightforwardly, and word error rates do not correlate well with downstream performance. We further find that the inclusion of audio features partially mitigates transcription errors, but that a naive usage of a multi-task setup does not.
%U https://aclanthology.org/2021.wassa-1.26
%P 250-256
Markdown (Informal)
[Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection](https://aclanthology.org/2021.wassa-1.26) (Culnan et al., WASSA 2021)
ACL
- John Culnan, Seongjin Park, Meghavarshini Krishnaswamy, and Rebecca Sharp. 2021. Me, myself, and ire: Effects of automatic transcription quality on emotion, sarcasm, and personality detection. In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 250–256, Online. Association for Computational Linguistics.