@inproceedings{westpfahl-schmidt-2016-folk,
title = "{FOLK}-Gold ― A Gold Standard for Part-of-Speech-Tagging of Spoken {G}erman",
author = "Westpfahl, Swantje and
Schmidt, Thomas",
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/L16-1237",
pages = "1493--1499",
abstract = {In this paper, we present a GOLD standard of part-of-speech tagged transcripts of spoken German. The GOLD standard data consists of four annotation layers ― transcription (modified orthography), normalization (standard orthography), lemmatization and POS tags ― all of which have undergone careful manual quality control. It comes with guidelines for the manual POS annotation of transcripts of German spoken data and an extended version of the STTS (Stuttgart T{\"u}bingen Tagset) which accounts for phenomena typically found in spontaneous spoken German. The GOLD standard was developed on the basis of the Research and Teaching Corpus of Spoken German, FOLK, and is, to our knowledge, the first such dataset based on a wide variety of spontaneous and authentic interaction types. It can be used as a basis for further development of language technology and corpus linguistic applications for German spoken language.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="westpfahl-schmidt-2016-folk">
<titleInfo>
<title>FOLK-Gold ― A Gold Standard for Part-of-Speech-Tagging of Spoken German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swantje</namePart>
<namePart type="family">Westpfahl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Schmidt</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>In this paper, we present a GOLD standard of part-of-speech tagged transcripts of spoken German. The GOLD standard data consists of four annotation layers ― transcription (modified orthography), normalization (standard orthography), lemmatization and POS tags ― all of which have undergone careful manual quality control. It comes with guidelines for the manual POS annotation of transcripts of German spoken data and an extended version of the STTS (Stuttgart Tübingen Tagset) which accounts for phenomena typically found in spontaneous spoken German. The GOLD standard was developed on the basis of the Research and Teaching Corpus of Spoken German, FOLK, and is, to our knowledge, the first such dataset based on a wide variety of spontaneous and authentic interaction types. It can be used as a basis for further development of language technology and corpus linguistic applications for German spoken language.</abstract>
<identifier type="citekey">westpfahl-schmidt-2016-folk</identifier>
<location>
<url>https://aclanthology.org/L16-1237</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1493</start>
<end>1499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FOLK-Gold ― A Gold Standard for Part-of-Speech-Tagging of Spoken German
%A Westpfahl, Swantje
%A Schmidt, Thomas
%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 westpfahl-schmidt-2016-folk
%X In this paper, we present a GOLD standard of part-of-speech tagged transcripts of spoken German. The GOLD standard data consists of four annotation layers ― transcription (modified orthography), normalization (standard orthography), lemmatization and POS tags ― all of which have undergone careful manual quality control. It comes with guidelines for the manual POS annotation of transcripts of German spoken data and an extended version of the STTS (Stuttgart Tübingen Tagset) which accounts for phenomena typically found in spontaneous spoken German. The GOLD standard was developed on the basis of the Research and Teaching Corpus of Spoken German, FOLK, and is, to our knowledge, the first such dataset based on a wide variety of spontaneous and authentic interaction types. It can be used as a basis for further development of language technology and corpus linguistic applications for German spoken language.
%U https://aclanthology.org/L16-1237
%P 1493-1499
Markdown (Informal)
[FOLK-Gold ― A Gold Standard for Part-of-Speech-Tagging of Spoken German](https://aclanthology.org/L16-1237) (Westpfahl & Schmidt, LREC 2016)
ACL