@inproceedings{gerlach-etal-2022-producing,
title = "Producing {S}tandard {G}erman Subtitles for {S}wiss {G}erman {TV} Content",
author = "Gerlach, Johanna and
Mutal, Jonathan and
Pierrette, Bouillon",
editor = "Ebling, Sarah and
Prud{'}hommeaux, Emily and
Vaidyanathan, Preethi",
booktitle = "Ninth Workshop on Speech and Language Processing for Assistive Technologies (SLPAT-2022)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.slpat-1.5",
doi = "10.18653/v1/2022.slpat-1.5",
pages = "37--43",
abstract = "In this study we compare two approaches (neural machine translation and edit-based) and the use of synthetic data for the task of translating normalised Swiss German ASR output into correct written Standard German for subtitles, with a special focus on syntactic differences. Results suggest that NMT is better suited to this task and that relatively simple rule-based generation of training data could be a valuable approach for cases where little training data is available and transformations are simple.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gerlach-etal-2022-producing">
<titleInfo>
<title>Producing Standard German Subtitles for Swiss German TV Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Mutal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bouillon</namePart>
<namePart type="family">Pierrette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Ninth Workshop on Speech and Language Processing for Assistive Technologies (SLPAT-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Ebling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Prud’hommeaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Vaidyanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study we compare two approaches (neural machine translation and edit-based) and the use of synthetic data for the task of translating normalised Swiss German ASR output into correct written Standard German for subtitles, with a special focus on syntactic differences. Results suggest that NMT is better suited to this task and that relatively simple rule-based generation of training data could be a valuable approach for cases where little training data is available and transformations are simple.</abstract>
<identifier type="citekey">gerlach-etal-2022-producing</identifier>
<identifier type="doi">10.18653/v1/2022.slpat-1.5</identifier>
<location>
<url>https://aclanthology.org/2022.slpat-1.5</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>37</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Producing Standard German Subtitles for Swiss German TV Content
%A Gerlach, Johanna
%A Mutal, Jonathan
%A Pierrette, Bouillon
%Y Ebling, Sarah
%Y Prud’hommeaux, Emily
%Y Vaidyanathan, Preethi
%S Ninth Workshop on Speech and Language Processing for Assistive Technologies (SLPAT-2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F gerlach-etal-2022-producing
%X In this study we compare two approaches (neural machine translation and edit-based) and the use of synthetic data for the task of translating normalised Swiss German ASR output into correct written Standard German for subtitles, with a special focus on syntactic differences. Results suggest that NMT is better suited to this task and that relatively simple rule-based generation of training data could be a valuable approach for cases where little training data is available and transformations are simple.
%R 10.18653/v1/2022.slpat-1.5
%U https://aclanthology.org/2022.slpat-1.5
%U https://doi.org/10.18653/v1/2022.slpat-1.5
%P 37-43
Markdown (Informal)
[Producing Standard German Subtitles for Swiss German TV Content](https://aclanthology.org/2022.slpat-1.5) (Gerlach et al., SLPAT 2022)
ACL