@inproceedings{bick-2020-annotated,
title = "An Annotated Social Media Corpus for {G}erman",
author = "Bick, Eckhard",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.752",
pages = "6127--6135",
abstract = "This paper presents the German Twitter section of a large (2 billion word) bilingual Social Media corpus for Hate Speech research, discussing the compilation, pseudonymization and grammatical annotation of the corpus, as well as special linguistic features and peculiarities encountered in the data. Among other things, compounding, accidental and intentional orthographic variation, gendering and the use of emoticons/emojis are addressed in a genre-specific fashion. We present the different layers of linguistic annotation (morphosyntactic, dependencies and semantic types) and explain how a general parser (GerGram) can be made to work on Social Media data, pointing out necessary adaptations and extensions. In an evaluation run on a random cross-section of tweets, the modified parser achieved F-scores of 97{\%} for morphology (fine-grained POS) and 92{\%} for syntax (labeled attachment score). Predictably, performance was twice as good in tweets with standard orthography than in tweets with spelling/casing irregularities or lack of sentence separation, the effect being more marked for morphology than for syntax.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bick-2020-annotated">
<titleInfo>
<title>An Annotated Social Media Corpus for German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eckhard</namePart>
<namePart type="family">Bick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper presents the German Twitter section of a large (2 billion word) bilingual Social Media corpus for Hate Speech research, discussing the compilation, pseudonymization and grammatical annotation of the corpus, as well as special linguistic features and peculiarities encountered in the data. Among other things, compounding, accidental and intentional orthographic variation, gendering and the use of emoticons/emojis are addressed in a genre-specific fashion. We present the different layers of linguistic annotation (morphosyntactic, dependencies and semantic types) and explain how a general parser (GerGram) can be made to work on Social Media data, pointing out necessary adaptations and extensions. In an evaluation run on a random cross-section of tweets, the modified parser achieved F-scores of 97% for morphology (fine-grained POS) and 92% for syntax (labeled attachment score). Predictably, performance was twice as good in tweets with standard orthography than in tweets with spelling/casing irregularities or lack of sentence separation, the effect being more marked for morphology than for syntax.</abstract>
<identifier type="citekey">bick-2020-annotated</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.752</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6127</start>
<end>6135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Annotated Social Media Corpus for German
%A Bick, Eckhard
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F bick-2020-annotated
%X This paper presents the German Twitter section of a large (2 billion word) bilingual Social Media corpus for Hate Speech research, discussing the compilation, pseudonymization and grammatical annotation of the corpus, as well as special linguistic features and peculiarities encountered in the data. Among other things, compounding, accidental and intentional orthographic variation, gendering and the use of emoticons/emojis are addressed in a genre-specific fashion. We present the different layers of linguistic annotation (morphosyntactic, dependencies and semantic types) and explain how a general parser (GerGram) can be made to work on Social Media data, pointing out necessary adaptations and extensions. In an evaluation run on a random cross-section of tweets, the modified parser achieved F-scores of 97% for morphology (fine-grained POS) and 92% for syntax (labeled attachment score). Predictably, performance was twice as good in tweets with standard orthography than in tweets with spelling/casing irregularities or lack of sentence separation, the effect being more marked for morphology than for syntax.
%U https://aclanthology.org/2020.lrec-1.752
%P 6127-6135
Markdown (Informal)
[An Annotated Social Media Corpus for German](https://aclanthology.org/2020.lrec-1.752) (Bick, LREC 2020)
ACL
- Eckhard Bick. 2020. An Annotated Social Media Corpus for German. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6127–6135, Marseille, France. European Language Resources Association.