@inproceedings{trippel-etal-2026-din,
title = "{DIN} 19461: A National Standard for Derived Text Formats",
author = {Trippel, Thorsten and
Barth, Florian and
Tello, Jose Calvo and
Du, Keli and
Gen{\^e}t, Philippe and
Kurzawe, Daniel and
Leinen, Peter and
Lendvai, Piroska and
Sch{\"o}ch, Christof and
Witt, Andreas and
Zimmermann, Arden},
editor = {Barth, Florian and
Du, Keli and
Calvo Tello, Jos{\'e} and
Gen{\^e}t, Philippe and
Lendvai, Piroska and
Sch{\"o}ch, Christof and
Trippel, Thorsten},
booktitle = "Proceedings of Leveraging Derived Text Formats to Unlock Copyrighted Collections for Open Science ({DTF}) @ {LREC} 2026",
month = jun,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.dtf-1.9/",
doi = "10.63317/3u92avo9gg59",
pages = "67--75",
abstract = "We present DIN{~}19461:2026-06 (E), a German draft national standard that defines categories, terminology, and process requirements for Derived Text Formats (DTFs) created from text documents in natural language. The standard specifies enrichment and information reduction operations, requirements for combining multiple DTFs, and documentation obligations for publication, archiving, and reuse. Its aim is to enable legally compliant sharing and analysis of texts{--}especially where copyright or data protection prevents distributing originals{--}while maintaining scientific utility and reproducibility through explicit process and parameter recording. We outline the scope, the key concepts, the four core reduction operations (retain, delete, replace, randomise), together with examples across token-, structure-, and vector-based DTFs, and implications for infrastructures (e.g., ISO 24622-based metadata). Finally, we discuss limitations, open questions (e.g., reconstruction risks with modern ML models), and next steps for adoption and maintenance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trippel-etal-2026-din">
<titleInfo>
<title>DIN 19461: A National Standard for Derived Text Formats</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thorsten</namePart>
<namePart type="family">Trippel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Barth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Calvo</namePart>
<namePart type="family">Tello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keli</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Genêt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Kurzawe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Leinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piroska</namePart>
<namePart type="family">Lendvai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Schöch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arden</namePart>
<namePart type="family">Zimmermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Leveraging Derived Text Formats to Unlock Copyrighted Collections for Open Science (DTF) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Barth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keli</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Calvo Tello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Genêt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piroska</namePart>
<namePart type="family">Lendvai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Schöch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thorsten</namePart>
<namePart type="family">Trippel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present DIN 19461:2026-06 (E), a German draft national standard that defines categories, terminology, and process requirements for Derived Text Formats (DTFs) created from text documents in natural language. The standard specifies enrichment and information reduction operations, requirements for combining multiple DTFs, and documentation obligations for publication, archiving, and reuse. Its aim is to enable legally compliant sharing and analysis of texts–especially where copyright or data protection prevents distributing originals–while maintaining scientific utility and reproducibility through explicit process and parameter recording. We outline the scope, the key concepts, the four core reduction operations (retain, delete, replace, randomise), together with examples across token-, structure-, and vector-based DTFs, and implications for infrastructures (e.g., ISO 24622-based metadata). Finally, we discuss limitations, open questions (e.g., reconstruction risks with modern ML models), and next steps for adoption and maintenance.</abstract>
<identifier type="citekey">trippel-etal-2026-din</identifier>
<identifier type="doi">10.63317/3u92avo9gg59</identifier>
<location>
<url>https://aclanthology.org/2026.dtf-1.9/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>67</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIN 19461: A National Standard for Derived Text Formats
%A Trippel, Thorsten
%A Barth, Florian
%A Tello, Jose Calvo
%A Du, Keli
%A Genêt, Philippe
%A Kurzawe, Daniel
%A Leinen, Peter
%A Lendvai, Piroska
%A Schöch, Christof
%A Witt, Andreas
%A Zimmermann, Arden
%Y Barth, Florian
%Y Du, Keli
%Y Calvo Tello, José
%Y Genêt, Philippe
%Y Lendvai, Piroska
%Y Schöch, Christof
%Y Trippel, Thorsten
%S Proceedings of Leveraging Derived Text Formats to Unlock Copyrighted Collections for Open Science (DTF) @ LREC 2026
%D 2026
%8 June
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F trippel-etal-2026-din
%X We present DIN 19461:2026-06 (E), a German draft national standard that defines categories, terminology, and process requirements for Derived Text Formats (DTFs) created from text documents in natural language. The standard specifies enrichment and information reduction operations, requirements for combining multiple DTFs, and documentation obligations for publication, archiving, and reuse. Its aim is to enable legally compliant sharing and analysis of texts–especially where copyright or data protection prevents distributing originals–while maintaining scientific utility and reproducibility through explicit process and parameter recording. We outline the scope, the key concepts, the four core reduction operations (retain, delete, replace, randomise), together with examples across token-, structure-, and vector-based DTFs, and implications for infrastructures (e.g., ISO 24622-based metadata). Finally, we discuss limitations, open questions (e.g., reconstruction risks with modern ML models), and next steps for adoption and maintenance.
%R 10.63317/3u92avo9gg59
%U https://aclanthology.org/2026.dtf-1.9/
%U https://doi.org/10.63317/3u92avo9gg59
%P 67-75
Markdown (Informal)
[DIN 19461: A National Standard for Derived Text Formats](https://aclanthology.org/2026.dtf-1.9/) (Trippel et al., DTF 2026)
ACL
- Thorsten Trippel, Florian Barth, Jose Calvo Tello, Keli Du, Philippe Genêt, Daniel Kurzawe, Peter Leinen, Piroska Lendvai, Christof Schöch, Andreas Witt, and Arden Zimmermann. 2026. DIN 19461: A National Standard for Derived Text Formats. In Proceedings of Leveraging Derived Text Formats to Unlock Copyrighted Collections for Open Science (DTF) @ LREC 2026, pages 67–75, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).