@inproceedings{schoch-2026-derived,
title = "Derived Text Formats as Strategic Transformations of In-Copyright Materials to Support Open Science: A Survey",
author = {Sch{\"o}ch, Christof},
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-1.1/",
doi = "10.63317/29k2v5o6rudf",
pages = "1--15",
abstract = "Derived Text Formats (DTFs) are the result of a strategic transformation of textual materials that are protected by copyright in their original form, such that the resulting data is useful for computational analyses and can be openly shared following best practices of Open Science without infringing copyright law. This paper aims to provide insights into several key aspects of this concept that is closely related to concepts such as corpus masking, non-consumptive research and extracted features. The paper establishes the motivation for using DTFs, discusses several foundational aspects of the concept and practice, describes ongoing research on issues including copyright, reconstructibility, evaluation and standardization of DTFs, and concludes with a roadmap for future work on DTFs. In this way, this paper provides a broad but concise overview of work on DTFs as a contribution to Open Science practices, with a focus on work in the Digital Humanities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schoch-2026-derived">
<titleInfo>
<title>Derived Text Formats as Strategic Transformations of In-Copyright Materials to Support Open Science: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Schöch</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>Derived Text Formats (DTFs) are the result of a strategic transformation of textual materials that are protected by copyright in their original form, such that the resulting data is useful for computational analyses and can be openly shared following best practices of Open Science without infringing copyright law. This paper aims to provide insights into several key aspects of this concept that is closely related to concepts such as corpus masking, non-consumptive research and extracted features. The paper establishes the motivation for using DTFs, discusses several foundational aspects of the concept and practice, describes ongoing research on issues including copyright, reconstructibility, evaluation and standardization of DTFs, and concludes with a roadmap for future work on DTFs. In this way, this paper provides a broad but concise overview of work on DTFs as a contribution to Open Science practices, with a focus on work in the Digital Humanities.</abstract>
<identifier type="citekey">schoch-2026-derived</identifier>
<identifier type="doi">10.63317/29k2v5o6rudf</identifier>
<location>
<url>https://aclanthology.org/2026.dtf-1.1/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>1</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Derived Text Formats as Strategic Transformations of In-Copyright Materials to Support Open Science: A Survey
%A Schöch, Christof
%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 schoch-2026-derived
%X Derived Text Formats (DTFs) are the result of a strategic transformation of textual materials that are protected by copyright in their original form, such that the resulting data is useful for computational analyses and can be openly shared following best practices of Open Science without infringing copyright law. This paper aims to provide insights into several key aspects of this concept that is closely related to concepts such as corpus masking, non-consumptive research and extracted features. The paper establishes the motivation for using DTFs, discusses several foundational aspects of the concept and practice, describes ongoing research on issues including copyright, reconstructibility, evaluation and standardization of DTFs, and concludes with a roadmap for future work on DTFs. In this way, this paper provides a broad but concise overview of work on DTFs as a contribution to Open Science practices, with a focus on work in the Digital Humanities.
%R 10.63317/29k2v5o6rudf
%U https://aclanthology.org/2026.dtf-1.1/
%U https://doi.org/10.63317/29k2v5o6rudf
%P 1-15
Markdown (Informal)
[Derived Text Formats as Strategic Transformations of In-Copyright Materials to Support Open Science: A Survey](https://aclanthology.org/2026.dtf-1.1/) (Schöch, DTF 2026)
ACL