@inproceedings{luecking-etal-2016-tgermacorp,
title = "{TG}erma{C}orp {--} A (Digital) Humanities Resource for (Computational) Linguistics",
author = "Luecking, Andy and
Hoenen, Armin and
Mehler, Alexander",
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/L16-1677",
pages = "4271--4277",
abstract = "TGermaCorp is a German text corpus whose primary sources are collected from German literature texts which date from the sixteenth century to the present. The corpus is intended to represent its target language (German) in syntactic, lexical, stylistic and chronological diversity. For this purpose, it is hand-annotated on several linguistic layers, including POS, lemma, named entities, multiword expressions, clauses, sentences and paragraphs. In order to introduce TGermaCorp in comparison to more homogeneous corpora of contemporary everyday language, quantitative assessments of syntactic and lexical diversity are provided. In this respect, TGermaCorp contributes to establishing characterising features for resource descriptions, which is needed for keeping track of a meaningful comparison of the ever-growing number of natural language resources. The assessments confirm the special role of proper names, whose propagation in text may influence lexical and syntactic diversity measures in rather trivial ways. TGermaCorp will be made available via hucompute.org.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luecking-etal-2016-tgermacorp">
<titleInfo>
<title>TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Luecking</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armin</namePart>
<namePart type="family">Hoenen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Mehler</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>TGermaCorp is a German text corpus whose primary sources are collected from German literature texts which date from the sixteenth century to the present. The corpus is intended to represent its target language (German) in syntactic, lexical, stylistic and chronological diversity. For this purpose, it is hand-annotated on several linguistic layers, including POS, lemma, named entities, multiword expressions, clauses, sentences and paragraphs. In order to introduce TGermaCorp in comparison to more homogeneous corpora of contemporary everyday language, quantitative assessments of syntactic and lexical diversity are provided. In this respect, TGermaCorp contributes to establishing characterising features for resource descriptions, which is needed for keeping track of a meaningful comparison of the ever-growing number of natural language resources. The assessments confirm the special role of proper names, whose propagation in text may influence lexical and syntactic diversity measures in rather trivial ways. TGermaCorp will be made available via hucompute.org.</abstract>
<identifier type="citekey">luecking-etal-2016-tgermacorp</identifier>
<location>
<url>https://aclanthology.org/L16-1677</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4271</start>
<end>4277</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics
%A Luecking, Andy
%A Hoenen, Armin
%A Mehler, Alexander
%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 luecking-etal-2016-tgermacorp
%X TGermaCorp is a German text corpus whose primary sources are collected from German literature texts which date from the sixteenth century to the present. The corpus is intended to represent its target language (German) in syntactic, lexical, stylistic and chronological diversity. For this purpose, it is hand-annotated on several linguistic layers, including POS, lemma, named entities, multiword expressions, clauses, sentences and paragraphs. In order to introduce TGermaCorp in comparison to more homogeneous corpora of contemporary everyday language, quantitative assessments of syntactic and lexical diversity are provided. In this respect, TGermaCorp contributes to establishing characterising features for resource descriptions, which is needed for keeping track of a meaningful comparison of the ever-growing number of natural language resources. The assessments confirm the special role of proper names, whose propagation in text may influence lexical and syntactic diversity measures in rather trivial ways. TGermaCorp will be made available via hucompute.org.
%U https://aclanthology.org/L16-1677
%P 4271-4277
Markdown (Informal)
[TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics](https://aclanthology.org/L16-1677) (Luecking et al., LREC 2016)
ACL