@inproceedings{mutal-etal-2023-improving,
title = "Improving {S}tandard {G}erman Captioning of Spoken {S}wiss {G}erman: Evaluating Multilingual Pre-trained Models",
author = "Mutal, Jonathan David and
Bouillon, Pierrette and
Gerlach, Johanna and
Starlander, Marianne",
editor = "Yamada, Masaru and
do Carmo, Felix",
booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-users.6",
pages = "65--76",
abstract = "Multilingual pre-trained language models are often the best alternative in low-resource settings. In the context of a cascade architecture for automatic Standard German captioning of spoken Swiss German, we evaluate different models on the task of transforming normalised Swiss German ASR output into Standard German. Instead of training a large model from scratch, we fine-tuned publicly available pre-trained models, which reduces the cost of training high-quality neural machine translation models. Results show that pre-trained multilingual models achieve the highest scores, and that a higher number of languages included in pre-training improves the performance. We also observed that the type of source and target included in fine-tuning data impacts the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mutal-etal-2023-improving">
<titleInfo>
<title>Improving Standard German Captioning of Spoken Swiss German: Evaluating Multilingual Pre-trained Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Mutal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Marianne</namePart>
<namePart type="family">Starlander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masaru</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">do Carmo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual pre-trained language models are often the best alternative in low-resource settings. In the context of a cascade architecture for automatic Standard German captioning of spoken Swiss German, we evaluate different models on the task of transforming normalised Swiss German ASR output into Standard German. Instead of training a large model from scratch, we fine-tuned publicly available pre-trained models, which reduces the cost of training high-quality neural machine translation models. Results show that pre-trained multilingual models achieve the highest scores, and that a higher number of languages included in pre-training improves the performance. We also observed that the type of source and target included in fine-tuning data impacts the results.</abstract>
<identifier type="citekey">mutal-etal-2023-improving</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-users.6</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>65</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Standard German Captioning of Spoken Swiss German: Evaluating Multilingual Pre-trained Models
%A Mutal, Jonathan David
%A Bouillon, Pierrette
%A Gerlach, Johanna
%A Starlander, Marianne
%Y Yamada, Masaru
%Y do Carmo, Felix
%S Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F mutal-etal-2023-improving
%X Multilingual pre-trained language models are often the best alternative in low-resource settings. In the context of a cascade architecture for automatic Standard German captioning of spoken Swiss German, we evaluate different models on the task of transforming normalised Swiss German ASR output into Standard German. Instead of training a large model from scratch, we fine-tuned publicly available pre-trained models, which reduces the cost of training high-quality neural machine translation models. Results show that pre-trained multilingual models achieve the highest scores, and that a higher number of languages included in pre-training improves the performance. We also observed that the type of source and target included in fine-tuning data impacts the results.
%U https://aclanthology.org/2023.mtsummit-users.6
%P 65-76
Markdown (Informal)
[Improving Standard German Captioning of Spoken Swiss German: Evaluating Multilingual Pre-trained Models](https://aclanthology.org/2023.mtsummit-users.6) (Mutal et al., MTSummit 2023)
ACL