@inproceedings{lambrecht-etal-2022-machine,
title = "Machine Translation from {S}tandard {G}erman to Alemannic Dialects",
author = "Lambrecht, Louisa and
Schneider, Felix and
Waibel, Alexander",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.sigul-1.17",
pages = "129--136",
abstract = "Machine translation has been researched using deep neural networks in recent years. These networks require lots of data to learn abstract representations of the input stored in continuous vectors. Dialect translation has become more important since the advent of social media. In particular, when dialect speakers and standard language speakers no longer understand each other, machine translation is of rising concern. Usually, dialect translation is a typical low-resourced language setting facing data scarcity problems. Additionally, spelling inconsistencies due to varying pronunciations and the lack of spelling rules complicate translation. This paper presents the best-performing approaches to handle these problems for Alemannic dialects. The results show that back-translation and conditioning on dialectal manifestations achieve the most remarkable enhancement over the baseline. Using back-translation, a significant gain of +4.5 over the strong transformer baseline of 37.3 BLEU points is accomplished. Differentiating between several Alemannic dialects instead of treating Alemannic as one dialect leads to substantial improvements: Multi-dialectal translation surpasses the baseline on the dialectal test sets. However, training individual models outperforms the multi-dialectal approach. There, improvements range from 7.5 to 10.6 BLEU points over the baseline depending on the dialect.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lambrecht-etal-2022-machine">
<titleInfo>
<title>Machine Translation from Standard German to Alemannic Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Louisa</namePart>
<namePart type="family">Lambrecht</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation has been researched using deep neural networks in recent years. These networks require lots of data to learn abstract representations of the input stored in continuous vectors. Dialect translation has become more important since the advent of social media. In particular, when dialect speakers and standard language speakers no longer understand each other, machine translation is of rising concern. Usually, dialect translation is a typical low-resourced language setting facing data scarcity problems. Additionally, spelling inconsistencies due to varying pronunciations and the lack of spelling rules complicate translation. This paper presents the best-performing approaches to handle these problems for Alemannic dialects. The results show that back-translation and conditioning on dialectal manifestations achieve the most remarkable enhancement over the baseline. Using back-translation, a significant gain of +4.5 over the strong transformer baseline of 37.3 BLEU points is accomplished. Differentiating between several Alemannic dialects instead of treating Alemannic as one dialect leads to substantial improvements: Multi-dialectal translation surpasses the baseline on the dialectal test sets. However, training individual models outperforms the multi-dialectal approach. There, improvements range from 7.5 to 10.6 BLEU points over the baseline depending on the dialect.</abstract>
<identifier type="citekey">lambrecht-etal-2022-machine</identifier>
<location>
<url>https://aclanthology.org/2022.sigul-1.17</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>129</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation from Standard German to Alemannic Dialects
%A Lambrecht, Louisa
%A Schneider, Felix
%A Waibel, Alexander
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lambrecht-etal-2022-machine
%X Machine translation has been researched using deep neural networks in recent years. These networks require lots of data to learn abstract representations of the input stored in continuous vectors. Dialect translation has become more important since the advent of social media. In particular, when dialect speakers and standard language speakers no longer understand each other, machine translation is of rising concern. Usually, dialect translation is a typical low-resourced language setting facing data scarcity problems. Additionally, spelling inconsistencies due to varying pronunciations and the lack of spelling rules complicate translation. This paper presents the best-performing approaches to handle these problems for Alemannic dialects. The results show that back-translation and conditioning on dialectal manifestations achieve the most remarkable enhancement over the baseline. Using back-translation, a significant gain of +4.5 over the strong transformer baseline of 37.3 BLEU points is accomplished. Differentiating between several Alemannic dialects instead of treating Alemannic as one dialect leads to substantial improvements: Multi-dialectal translation surpasses the baseline on the dialectal test sets. However, training individual models outperforms the multi-dialectal approach. There, improvements range from 7.5 to 10.6 BLEU points over the baseline depending on the dialect.
%U https://aclanthology.org/2022.sigul-1.17
%P 129-136
Markdown (Informal)
[Machine Translation from Standard German to Alemannic Dialects](https://aclanthology.org/2022.sigul-1.17) (Lambrecht et al., SIGUL 2022)
ACL
- Louisa Lambrecht, Felix Schneider, and Alexander Waibel. 2022. Machine Translation from Standard German to Alemannic Dialects. In Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, pages 129–136, Marseille, France. European Language Resources Association.