@inproceedings{krieg-holz-etal-2016-code,
title = "{C}od{E} Alltag: A {G}erman-Language {E}-Mail Corpus",
author = "Krieg-Holz, Ulrike and
Schuschnig, Christian and
Matthies, Franz and
Redling, Benjamin and
Hahn, Udo",
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/L16-1404",
pages = "2543--2550",
abstract = "We introduce CODE ALLTAG, a text corpus composed of German-language e-mails. It is divided into two partitions: the first of these portions, CODE ALLTAG{\_}XL, consists of a bulk-size collection drawn from an openly accessible e-mail archive (roughly 1.5M e-mails), whereas the second portion, CODE ALLTAG{\_}S+d, is much smaller in size (less than thousand e-mails), yet excels with demographic data from each author of an e-mail. CODE ALLTAG, thus, currently constitutes the largest E-Mail corpus ever built. In this paper, we describe, for both parts, the solicitation process for gathering e-mails, present descriptive statistical properties of the corpus, and, for CODE ALLTAG{\_}S+d, reveal a compilation of demographic features of the donors of e-mails.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krieg-holz-etal-2016-code">
<titleInfo>
<title>CodE Alltag: A German-Language E-Mail Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrike</namePart>
<namePart type="family">Krieg-Holz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Schuschnig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franz</namePart>
<namePart type="family">Matthies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Redling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</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>
<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>We introduce CODE ALLTAG, a text corpus composed of German-language e-mails. It is divided into two partitions: the first of these portions, CODE ALLTAG_XL, consists of a bulk-size collection drawn from an openly accessible e-mail archive (roughly 1.5M e-mails), whereas the second portion, CODE ALLTAG_S+d, is much smaller in size (less than thousand e-mails), yet excels with demographic data from each author of an e-mail. CODE ALLTAG, thus, currently constitutes the largest E-Mail corpus ever built. In this paper, we describe, for both parts, the solicitation process for gathering e-mails, present descriptive statistical properties of the corpus, and, for CODE ALLTAG_S+d, reveal a compilation of demographic features of the donors of e-mails.</abstract>
<identifier type="citekey">krieg-holz-etal-2016-code</identifier>
<location>
<url>https://aclanthology.org/L16-1404</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>2543</start>
<end>2550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CodE Alltag: A German-Language E-Mail Corpus
%A Krieg-Holz, Ulrike
%A Schuschnig, Christian
%A Matthies, Franz
%A Redling, Benjamin
%A Hahn, Udo
%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 krieg-holz-etal-2016-code
%X We introduce CODE ALLTAG, a text corpus composed of German-language e-mails. It is divided into two partitions: the first of these portions, CODE ALLTAG_XL, consists of a bulk-size collection drawn from an openly accessible e-mail archive (roughly 1.5M e-mails), whereas the second portion, CODE ALLTAG_S+d, is much smaller in size (less than thousand e-mails), yet excels with demographic data from each author of an e-mail. CODE ALLTAG, thus, currently constitutes the largest E-Mail corpus ever built. In this paper, we describe, for both parts, the solicitation process for gathering e-mails, present descriptive statistical properties of the corpus, and, for CODE ALLTAG_S+d, reveal a compilation of demographic features of the donors of e-mails.
%U https://aclanthology.org/L16-1404
%P 2543-2550
Markdown (Informal)
[CodE Alltag: A German-Language E-Mail Corpus](https://aclanthology.org/L16-1404) (Krieg-Holz et al., LREC 2016)
ACL
- Ulrike Krieg-Holz, Christian Schuschnig, Franz Matthies, Benjamin Redling, and Udo Hahn. 2016. CodE Alltag: A German-Language E-Mail Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2543–2550, Portorož, Slovenia. European Language Resources Association (ELRA).