@inproceedings{samardzic-etal-2016-archimob,
title = "{A}rchi{M}ob - A Corpus of Spoken {S}wiss {G}erman",
author = "Samard\v zi\'c, Tanja and
Scherrer, Yves and
Glaser, Elvira",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro\v z, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1641/",
pages = "4061--4066",
abstract = "Swiss dialects of German are, unlike most dialects of well standardised languages, widely used in everyday communication. Despite this fact, automatic processing of Swiss German is still a considerable challenge due to the fact that it is mostly a spoken variety rarely recorded and that it is subject to considerable regional variation. This paper presents a freely available general-purpose corpus of spoken Swiss German suitable for linguistic research, but also for training automatic tools. The corpus is a result of a long design process, intensive manual work and specially adapted computational processing. We first describe how the documents were transcribed, segmented and aligned with the sound source, and how inconsistent transcriptions were unified through an additional normalisation layer. We then present a bootstrapping approach to automatic normalisation using different machine-translation-inspired methods. Furthermore, we evaluate the performance of part-of-speech taggers on our data and show how the same bootstrapping approach improves part-of-speech tagging by 10\% over four rounds. Finally, we present the modalities of access of the corpus as well as the data format."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samardzic-etal-2016-archimob">
<titleInfo>
<title>ArchiMob - A Corpus of Spoken Swiss German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Samardžić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elvira</namePart>
<namePart type="family">Glaser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Swiss dialects of German are, unlike most dialects of well standardised languages, widely used in everyday communication. Despite this fact, automatic processing of Swiss German is still a considerable challenge due to the fact that it is mostly a spoken variety rarely recorded and that it is subject to considerable regional variation. This paper presents a freely available general-purpose corpus of spoken Swiss German suitable for linguistic research, but also for training automatic tools. The corpus is a result of a long design process, intensive manual work and specially adapted computational processing. We first describe how the documents were transcribed, segmented and aligned with the sound source, and how inconsistent transcriptions were unified through an additional normalisation layer. We then present a bootstrapping approach to automatic normalisation using different machine-translation-inspired methods. Furthermore, we evaluate the performance of part-of-speech taggers on our data and show how the same bootstrapping approach improves part-of-speech tagging by 10% over four rounds. Finally, we present the modalities of access of the corpus as well as the data format.</abstract>
<identifier type="citekey">samardzic-etal-2016-archimob</identifier>
<location>
<url>https://aclanthology.org/L16-1641/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4061</start>
<end>4066</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArchiMob - A Corpus of Spoken Swiss German
%A Samardžić, Tanja
%A Scherrer, Yves
%A Glaser, Elvira
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F samardzic-etal-2016-archimob
%X Swiss dialects of German are, unlike most dialects of well standardised languages, widely used in everyday communication. Despite this fact, automatic processing of Swiss German is still a considerable challenge due to the fact that it is mostly a spoken variety rarely recorded and that it is subject to considerable regional variation. This paper presents a freely available general-purpose corpus of spoken Swiss German suitable for linguistic research, but also for training automatic tools. The corpus is a result of a long design process, intensive manual work and specially adapted computational processing. We first describe how the documents were transcribed, segmented and aligned with the sound source, and how inconsistent transcriptions were unified through an additional normalisation layer. We then present a bootstrapping approach to automatic normalisation using different machine-translation-inspired methods. Furthermore, we evaluate the performance of part-of-speech taggers on our data and show how the same bootstrapping approach improves part-of-speech tagging by 10% over four rounds. Finally, we present the modalities of access of the corpus as well as the data format.
%U https://aclanthology.org/L16-1641/
%P 4061-4066
Markdown (Informal)
[ArchiMob - A Corpus of Spoken Swiss German](https://aclanthology.org/L16-1641/) (Samardžić et al., LREC 2016)
ACL
- Tanja Samardžić, Yves Scherrer, and Elvira Glaser. 2016. ArchiMob - A Corpus of Spoken Swiss German. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4061–4066, Portorož, Slovenia. European Language Resources Association (ELRA).