Faculty of Language, Literature and Humanities - Corpus Linguistics and Morphology

@article{shadrova_step_2025,
	title = {„{Step} away from the {Computer}!“: Über die linguistische {Datenkategorisierung} als {Erkenntnisprozess} und daraus folgende {Herausforderungen} bei der {Nachnutzung} von {Annotationen} und {Annotationstools}},
	volume = {53},
	issn = {1613-0626, 0301-3294},
	shorttitle = {„{Step} away from the {Computer}!“},
	url = {https://www.degruyterbrill.com/document/doi/10.1515/zgl-2025-2005/html},
	doi = {10.1515/zgl-2025-2005},
	abstract = {Abstract
            Linguistic research frequently requires the categorization of language phenomena in corpus data (annotation). Since those may occur plentifully, a partial or full automation of the annotation process appears attractive. The filtering and recombination of existing annotation layers seems to further provide an elegant solution to the deduction of higher-level annotations. In this contribution, we show at the example of German split particle verbs that this approach results in a number of linguistic, technological, and epistemological challenges related to the precise definition of the various models employed and their interfaces. We argue that the manual annotation of corpus data is not merely a preprocessing task, but is itself an epistemological process central to the development of linguistic theory. We discuss why machine-based language processing can neither mimic nor replace this process; why it can generally not reach a level of precision that would be suitable for linguistic research without further integration, adaptation, and manual correction; and how its blind application systematically skews results in crucial areas of research. We close with the suggestion of several best practice approaches which help to prevent and resolve incompatibilities and delays arising from common problems of corpus-based language modeling.},
	language = {en},
	number = {1},
	urldate = {2025-04-11},
	journal = {Zeitschrift für germanistische Linguistik},
	author = {Shadrova, Anna and Lüdeling, Anke and Klotz, Martin and Hartz, Rahel Gajaneh and Krause, Thomas},
	month = apr,
	year = {2025},
	pages = {166--214},
}

Abstract Linguistic research frequently requires the categorization of language phenomena in corpus data (annotation). Since those may occur plentifully, a partial or full automation of the annotation process appears attractive. The filtering and recombination of existing annotation layers seems to further provide an elegant solution to the deduction of higher-level annotations. In this contribution, we show at the example of German split particle verbs that this approach results in a number of linguistic, technological, and epistemological challenges related to the precise definition of the various models employed and their interfaces. We argue that the manual annotation of corpus data is not merely a preprocessing task, but is itself an epistemological process central to the development of linguistic theory. We discuss why machine-based language processing can neither mimic nor replace this process; why it can generally not reach a level of precision that would be suitable for linguistic research without further integration, adaptation, and manual correction; and how its blind application systematically skews results in crucial areas of research. We close with the suggestion of several best practice approaches which help to prevent and resolve incompatibilities and delays arising from common problems of corpus-based language modeling.

@incollection{coniglio_ressource_2024,
	address = {Göttingen},
	title = {Eine {Ressource} durch {Abwägung}: {Wie} bestehende generische {Softwarelösungen} ‚über sich hinauswachsen‘ und ein {Parallelkorpus} ermöglichen},
	copyright = {https://creativecommons.org/licenses/by-sa/4.0/deed.de},
	isbn = {978-3-86395-599-1},
	shorttitle = {Eine {Ressource} durch {Abwägung}},
	url = {https://univerlag.uni-goettingen.de/handle/3/isbn-978-3-86395-599-1.5},
	urldate = {2024-12-02},
	booktitle = {Mittelniederdeutsch zwischen {Korpuslinguistik} und {Literaturwissenschaft}},
	publisher = {Göttingen University Press},
	author = {Klotz, Martin and Krause, Thomas},
	editor = {Coniglio, Marco and Recker, Anabel and Sahm, Heike},
	year = {2024},
	doi = {10.17875/gup2024-2620},
	pages = {123--138},
}

@article{ludeling_register_2024,
	title = {Register: {Language} {Users}’ {Knowledge} of {Situational}-{Functional} {Variation}},
	volume = {3},
	shorttitle = {Register},
	url = {http://edoc.hu-berlin.de/18452/30567},
	doi = {10.18452/29131},
	abstract = {The goal of the CRC 1412 “Register: Language Users’ Knowledge of Situational- Functional Variation” is to answer the overarching research question “What consti- tutes a language user’s register knowledge?”. Our starting point is the observation that many situational and functional parameters – such as the relation between the interlocutors, the purpose of a conversation, the formality of the setting, etc. – influence the way speakers use language. Speakers seem to know which linguistic behavior is appropriate in which situation, typically without having been explicitly made aware of it. This is what we call register knowledge and The purpose of this CRC is to enhance our understanding of the role of register knowledge in language use, acquisition, processing, variation, and change; and develop a general theory of register knowledge to complement current linguistic models. In Phase I, we found that register is pervasive on all linguistic levels and is mostly non-categorial. In Phase II, we will be concerned with the integration of the findings into models of grammar, acquisition, variation, change, and processing.},
	language = {eng},
	number = {1},
	urldate = {2024-11-11},
	journal = {Register Aspects of Language in Situation},
	author = {Lüdeling, Anke and Szucsich, Luka and Zeige, Lars Erik and Adli, Aria and Alexiadou, Artemis and Belz, Malte and Bouzouita, Miriam and Bunk, Oliver and Dreyer, Malte and Egg, Markus and Feulner, Anna Helene and Fleischer, Jürg and Gagarina, Natalia and Hirsch, Aron and Jannedy, Stefanie and Knoeferle, Pia and Krause, Thomas and Kutscher, Silvia and Liu, Mingya and Lütke, Beate and Machicao y Priemer, Antonio and Maquate, Katja and Merino Hernández, Laura and Meyer, Roland and Mooshammer, Christine and Müller, Stefan and Sauerland, Uli and Sauermann, Antje and Schmitt, Viola and Schumacher, Nicole and Serova, Dina and Solt, Stephanie and Vander Klok, Jozina and Verhoeven, Elisabeth and Waltereit, Richard and Weirich, Melanie and Wiese, Heike},
	year = {2024},
	note = {Publisher: Sprach- und literaturwissenschaftliche Fakultät},
	pages = {1--53},
}

The goal of the CRC 1412 “Register: Language Users’ Knowledge of Situational- Functional Variation” is to answer the overarching research question “What consti- tutes a language user’s register knowledge?”. Our starting point is the observation that many situational and functional parameters – such as the relation between the interlocutors, the purpose of a conversation, the formality of the setting, etc. – influence the way speakers use language. Speakers seem to know which linguistic behavior is appropriate in which situation, typically without having been explicitly made aware of it. This is what we call register knowledge and The purpose of this CRC is to enhance our understanding of the role of register knowledge in language use, acquisition, processing, variation, and change; and develop a general theory of register knowledge to complement current linguistic models. In Phase I, we found that register is pervasive on all linguistic levels and is mostly non-categorial. In Phase II, we will be concerned with the integration of the findings into models of grammar, acquisition, variation, change, and processing.

@article{druskat_hexatomic_2023,
	title = {Hexatomic: {An} extensible, {OS}-independent platform for deep multi-layer linguistic annotation of corpora},
	volume = {8},
	url = {https://doi.org/10.21105/joss.04825},
	doi = {10.21105/joss.04825},
	number = {86},
	journal = {Journal of Open Source Software},
	author = {Druskat, Stephan and Krause, Thomas and Lachenmaier, Clara and Bunzeck, Bastian},
	year = {2023},
	note = {Publisher: The Open Journal},
	pages = {4825},
}

@misc{druskat_four_2023,
	address = {Paderborn},
	title = {The four elements of achieving research software sustainability for long tail projects},
	url = {https://doi.org/10.5281/zenodo.7654777},
	abstract = {At deRSE19 we presented Hexatomic, a project to investigate what small research software projects need to make their software more sustainable. This talk reports our results. Developing annotation software for multi-layer linguistic corpora, we found that

    there is a minimal infrastructure that needs to be in place to activate a potential for sustainability in the first place, and
    that four elements play key roles in reducing the risk of software collapse.

These four elements are: a clearly defined, resourced maintainer role; multi-modal documentation to guide maintenance and use; automated tests; code review and triage processes supported by static code analysis. We have tested this by performing changes in maintainership and observing success in reviving development and maintenance activities. Our results furthermore clearly point to the necessity for RSEs to be involved in software projects as part of research projects. In this talk, we describe our research project, the minimal infrastructure as well as development, maintenance, and release and publication workflows we implemented, and how the four elements helped maintainers take up their roles.},
	language = {English},
	author = {Druskat, Stephan and Krause, Thomas},
	month = feb,
	year = {2023},
}

At deRSE19 we presented Hexatomic, a project to investigate what small research software projects need to make their software more sustainable. This talk reports our results. Developing annotation software for multi-layer linguistic corpora, we found that there is a minimal infrastructure that needs to be in place to activate a potential for sustainability in the first place, and that four elements play key roles in reducing the risk of software collapse. These four elements are: a clearly defined, resourced maintainer role; multi-modal documentation to guide maintenance and use; automated tests; code review and triage processes supported by static code analysis. We have tested this by performing changes in maintainership and observing success in reviving development and maintenance activities. Our results furthermore clearly point to the necessity for RSEs to be involved in software projects as part of research projects. In this talk, we describe our research project, the minimal infrastructure as well as development, maintenance, and release and publication workflows we implemented, and how the four elements helped maintainers take up their roles.

@misc{krause_graphannis_2022,
	title = {{graphANNIS} 2.2.2},
	url = {https://github.com/korpling/graphANNIS},
	author = {Krause, Thomas},
	month = jul,
	year = {2022},
	doi = {10.5281/zenodo.2598164},
}

@misc{krause_annis_2022,
	title = {{ANNIS} 4.9.5},
	copyright = {Apache-2.0},
	url = {https://github.com/korpling/ANNIS},
	author = {Krause, Thomas and Benjamin, Weißenfels and Rütte, Tom and Glushanok, Irina and Klotz, Martin and Zhang, Shuo and Zeldes, Amir and Bartels, Fabian and Druskat, Stephan and Boyd, Adriane and Stemle, Egon and Lampen, Lari and Petran, Florian},
	month = jul,
	year = {2022},
	doi = {10.5281/zenodo.1212548},
}

@article{ludeling_register_2022,
	title = {Register: {Language} {Users}’ {Knowledge} of {Situational}-{Functional} {Variation}},
	copyright = {(CC BY 4.0) Attribution 4.0 International},
	issn = {2750-9370},
	shorttitle = {Register},
	url = {https://edoc.hu-berlin.de/handle/18452/25891},
	doi = {10.18452/24901},
	abstract = {The Collaborative Research Center 1412 “Register: Language Users’ Knowledge of Situational-Functional Variation” (CRC 1412) investigates the role of register in language, focusing in particular on what constitutes a language user’s register knowledge and which situational-functional factors determine a user’s choices. The following paper is an extract from the frame text of the proposal for the CRC 1412, which was submitted to the Deutsche Forschungsgemeinschaft in 2019, followed by a successful onsite evaluation that took place in 2019. The CRC 1412 then started its work on January 1, 2020. The theoretical part of the frame text gives an extensive overview of the theoretical and empirical perspectives on register knowledge from the viewpoint of 2019. Due to the high collaborative effort of all PIs involved, the frame text is unique in its scope on register research, encompassing register-relevant aspects from variationist approaches, psycholinguistics, grammatical theory, acquisition theory, historical linguistics, phonology, phonetics, typology, corpus linguistics, and computational linguistics, as well as qualitative and quantitative modeling. Although our positions and hypotheses since its submission have developed further, the frame text is still a vital resource as a compilation of state-of-the-art register research and a documentation of the start of the CRC 1412. The theoretical part without administrative components therefore presents an ideal starter publication to kick off the CRC’s publication series REALIS. For an overview of the projects and more information on the CRC, see https://sfb1412.hu-berlin.de/.},
	language = {eng},
	urldate = {2022-10-24},
	author = {Lüdeling, Anke and Alexiadou, Artemis and Adli, Aria and Donhauser, Karin and Dreyer, Malte and Egg, Markus and Feulner, Anna Helene and Gagarina, Natalia and Hock, Wolfgang and Jannedy, Stefanie and Kammerzell, Frank and Knoeferle, Pia and Krause, Thomas and Krifka, Manfred and Kutscher, Silvia and Lütke, Beate and McFadden, Thomas and Meyer, Roland and Mooshammer, Christine and Müller, Stefan and Maquate, Katja and Norde, Muriel and Sauerland, Uli and Solt, Stephanie and Szucsich, Luka and Verhoeven, Elisabeth and Waltereit, Richard and Wolfsgruber, Anne and Zeige, Lars Erik},
	month = jul,
	year = {2022},
	note = {Accepted: 2022-08-24T08:42:50Z
Publisher: Humboldt-Universität zu Berlin},
}

The Collaborative Research Center 1412 “Register: Language Users’ Knowledge of Situational-Functional Variation” (CRC 1412) investigates the role of register in language, focusing in particular on what constitutes a language user’s register knowledge and which situational-functional factors determine a user’s choices. The following paper is an extract from the frame text of the proposal for the CRC 1412, which was submitted to the Deutsche Forschungsgemeinschaft in 2019, followed by a successful onsite evaluation that took place in 2019. The CRC 1412 then started its work on January 1, 2020. The theoretical part of the frame text gives an extensive overview of the theoretical and empirical perspectives on register knowledge from the viewpoint of 2019. Due to the high collaborative effort of all PIs involved, the frame text is unique in its scope on register research, encompassing register-relevant aspects from variationist approaches, psycholinguistics, grammatical theory, acquisition theory, historical linguistics, phonology, phonetics, typology, corpus linguistics, and computational linguistics, as well as qualitative and quantitative modeling. Although our positions and hypotheses since its submission have developed further, the frame text is still a vital resource as a compilation of state-of-the-art register research and a documentation of the start of the CRC 1412. The theoretical part without administrative components therefore presents an ideal starter publication to kick off the CRC’s publication series REALIS. For an overview of the projects and more information on the CRC, see https://sfb1412.hu-berlin.de/.

@misc{ludeling_what_2021,
	address = {Berlin},
	title = {What is a good corpus?},
	url = {https://rolandschaefer.net/wp-content/uploads/2021/06/GoodCorpusSFB1412Handout.pdf},
	author = {Lüdeling, Anke and Schäfer, Roland and Pankratz, Elizabeth and Krause, Thomas and Bildhauer, Felix and Golcher, Felix},
	month = mar,
	year = {2021},
	note = {A series of three talks given in the colloquium of the CRC (SFB) 1412 Register.},
}

@misc{wiese_heike_rueg_2020,
	title = {{RUEG} {Corpus}},
	url = {https://doi.org/10.5281/zenodo.3765218},
	publisher = {Zenodo},
	author = {Wiese, Heike and Alexiadou, Artemis and Allen, Shanley and Bunk, Oliver and Gagarina, Natalia and Iefremenko, Kateryna and Jahns, Esther and Klotz, Martin and Krause, Thomas and Labrenz, Annika and Lüdeling, Anke and Martynova, Maria and Neuhaus, Katrin and Pashkova, Tatiana and Rizou, Vicky and Rosemarie, Tracy and Schroeder, Christoph and Szucsich, Luka and Tsehaye, Wintai and Zerbian, Sabine and Zuban, Yulia},
	month = apr,
	year = {2020},
}

@misc{krause_hard_2019,
	address = {Potsdam},
	title = {Die {Hard} 1.1024.0: backward compatibility of a search engine with persistant {IDs}},
	url = {https://doi.org/10.5446/42501},
	abstract = {Semantic versioning can be used to describe the downward compatibility of software. Using the example of a search engine for linguistic annotations, we show which problems can occur when operating a search-based service with persistent IDs for queries and results and present possible solutions. Different components, such as the software, the domain-specific query language, and the web service, provide different guarantees and make different demands on downward compatibility. By migrating an existing PostgreSQL-based system to our own implementation, we gain important practical experience in the downward-compatible modernization of an existing system, which we will share in this talk.},
	author = {Krause, Thomas and Druskat, Stephan},
	month = jun,
	year = {2019},
	note = {deRSE19 - Conference for Research Software Engineers in Germany},
}

Semantic versioning can be used to describe the downward compatibility of software. Using the example of a search engine for linguistic annotations, we show which problems can occur when operating a search-based service with persistent IDs for queries and results and present possible solutions. Different components, such as the software, the domain-specific query language, and the web service, provide different guarantees and make different demands on downward compatibility. By migrating an existing PostgreSQL-based system to our own implementation, we gain important practical experience in the downward-compatible modernization of an existing system, which we will share in this talk.

@phdthesis{krause_annis:_2019,
	type = {Doctoral {Dissertation}},
	title = {{ANNIS}: {A} graph-based query system for deeply annotated text corpora},
	copyright = {All rights reserved},
	url = {https://doi.org/10.18452/19659},
	school = {Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät},
	author = {Krause, Thomas},
	year = {2019},
	doi = {10.18452/19659},
}

@inproceedings{hanno_biber_designing_2018,
	address = {Miyazaki, Japan},
	title = {Designing a {Re}-{Usable} and {Embeddable} {Corpus} {Search} {Library}},
	copyright = {All rights reserved},
	isbn = {979-10-95546-14-6},
	url = {http://lrec-conf.org/workshops/lrec2018/W17/pdf/12_W17.pdf},
	language = {english},
	booktitle = {Proceedings of the {Eleventh} {International} {Conference} on {Language} {Resources} and {Evaluation} ({LREC} 2018)},
	publisher = {European Language Resources Association (ELRA)},
	author = {Krause, Thomas and Leser, Ulf and Lüdeling, Anke and Druskat, Stephan},
	editor = {{Hanno Biber} and Breiteneder, Evelyn and Clematide, Simon and Witt, Andreas},
	month = dec,
	year = {2018},
}

@article{OdebrechtEtAl2017,
	title = {{RIDGES} {Herbology}: designing a diachronic multi-layer corpus},
	volume = {51},
	copyright = {All rights reserved},
	issn = {1574-0218},
	doi = {10.1007/s10579-016-9374-3},
	abstract = {This paper introduces a multi-layer corpus architecture with multiple tokenizations using the open source historical, diachronic corpus of German called Register in Diachronic German Science. The corpus contains herbal texts printed between the fifteenth and nineteenth centuries and is concerned with the development of a German scientific register, independent of Latin. We will discuss difficulties of transcribing, normalizing and annotating historical texts and will thereby argue for the advantages of multiple layers and multiple tokenizations. A virtually infinite number of annotations can be added to the corpus, without the need for deciding between or discarding interpretations. Thus, this flexible architecture enables multiple normalizations and types of annotation and is open to a wide range of research questions in the humanities. We provide case studies concerning the exploitation of our different normalizations as well as structural, register-specific and linguistic annotations. The corpus architecture allows for its reuse as a resource for corpus-based research approaches.},
	number = {3},
	journal = {Language Resources and Evaluation},
	author = {Odebrecht, Carolin and Belz, Malte and Zeldes, Amir and Lüdeling, Anke and Krause, Thomas},
	month = sep,
	year = {2017},
	pages = {695--725},
}

This paper introduces a multi-layer corpus architecture with multiple tokenizations using the open source historical, diachronic corpus of German called Register in Diachronic German Science. The corpus contains herbal texts printed between the fifteenth and nineteenth centuries and is concerned with the development of a German scientific register, independent of Latin. We will discuss difficulties of transcribing, normalizing and annotating historical texts and will thereby argue for the advantages of multiple layers and multiple tokenizations. A virtually infinite number of annotations can be added to the corpus, without the need for deciding between or discarding interpretations. Thus, this flexible architecture enables multiple normalizations and types of annotation and is open to a wide range of research questions in the humanities. We provide case studies concerning the exploitation of our different normalizations as well as structural, register-specific and linguistic annotations. The corpus architecture allows for its reuse as a resource for corpus-based research approaches.

@inproceedings{odebrecht_zwei_2017,
	address = {Bern},
	title = {Zwei grundlegende {Fragen} der digitalen {Nachhaltigkeit}: {Wie} können wir die heterogenen {Forschungsfragen} und die {Community} bei der {Verfügbarmachung} von {Forschungsdaten} miteinbeziehen?},
	copyright = {All rights reserved},
	url = {http://www.dhd2017.ch/wp-content/uploads/2017/01/Abstractband_def_24.1.17-1.pdf},
	booktitle = {Digitale {Nachhaltigkeit}. {DHd} 2017},
	author = {Odebrecht, Carolin and Dreyer, Malte and Lüdeling, Anke and Krause, Thomas},
	month = feb,
	year = {2017},
}

@article{krause_annis3_2016,
	title = {{ANNIS3}: {A} new architecture for generic corpus query and visualization},
	volume = {31},
	copyright = {All rights reserved},
	issn = {2055-7671},
	doi = {10.1093/llc/fqu057},
	abstract = {This article is concerned with the data structures, properties of query languages, and visualization facilities required for the generic representation of richly annotated, heterogeneous linguistic corpora. We propose that above and beyond a general graph-based data model, which is becoming increasingly popular in many complex annotation formats, a well-defined concept of multiple, potentially conflicting segmentation layers must be introduced to deal with different sources and applications of corpus data flexibly. We also propose a generic solution for specialized corpus visualizations in a Web interface using annotation-triggered style sheets, which leverage the power of modern browsers and CSS for multiple and highly customizable views of primary data. We offer an implementation and evaluation of our architecture in ANNIS3, an open-source browser-based architecture for corpus search and visualization. We present three case studies to test the coverage of the system, encompassing core linguistic and digital humanities use-cases including richly annotated newspaper treebanks, multilingual diplomatic and normalized manuscript materials edited in TEI, and analysis of multimodal recordings of spoken language.},
	number = {1},
	journal = {Digital Scholarship in the Humanities},
	author = {Krause, Thomas and Zeldes, Amir},
	year = {2016},
	pages = {118--139},
}

This article is concerned with the data structures, properties of query languages, and visualization facilities required for the generic representation of richly annotated, heterogeneous linguistic corpora. We propose that above and beyond a general graph-based data model, which is becoming increasingly popular in many complex annotation formats, a well-defined concept of multiple, potentially conflicting segmentation layers must be introduced to deal with different sources and applications of corpus data flexibly. We also propose a generic solution for specialized corpus visualizations in a Web interface using annotation-triggered style sheets, which leverage the power of modern browsers and CSS for multiple and highly customizable views of primary data. We offer an implementation and evaluation of our architecture in ANNIS3, an open-source browser-based architecture for corpus search and visualization. We present three case studies to test the coverage of the system, encompassing core linguistic and digital humanities use-cases including richly annotated newspaper treebanks, multilingual diplomatic and normalized manuscript materials edited in TEI, and analysis of multimodal recordings of spoken language.

@misc{druskat_utilising_2016,
	address = {Hamburg},
	title = {Utilising {ANNIS} for search and analysis of historical data},
	url = {http://doi.org/10.5281/zenodo.160368},
	author = {Druskat, Stephan and Krause, Thomas and Odebrecht, Carolin},
	month = sep,
	year = {2016},
	note = {Reuse or New Development: sustainability of resources and tools for multi-facetted historical data and languages. Workshop in conjuction with the Conference
Forschungsdaten in den Geisteswissenschaften (FORGE 2016) "Jenseits der Daten"},
}

@techreport{mellmann_berlin_2016,
	title = {Berlin {United} - {Nao} {Team} {Humboldt}: {Team} {Report} 2016},
	url = {http://www.naoteamhumboldt.de/wp-content/papercite-data/pdf/2016-Naoth-Report.pdf},
	institution = {Humboldt-Universität zu Berlin, Adaptive Systems Group},
	author = {Mellmann, Heinrich and Schlotter, Benjamin and Kaden, Steffen and Strobel, Philipp and Krause, Thomas and Ritter, Claas-Norman},
	year = {2016},
}

@article{krause_graphannis:_2016,
	title = {{graphANNIS}: {A} {Fast} {Query} {Engine} for {Deeply} {Annotated} {Linguistic} {Corpora}},
	volume = {31},
	copyright = {All rights reserved},
	url = {http://www.jlcl.org/2016_Heft1/jlcl-2016-1-1KrauseEtAl.pdf},
	number = {1},
	journal = {JLCL},
	author = {Krause, Thomas and Leser, Ulf and Lüdeling, Anke},
	year = {2016},
	pages = {iii--25},
}

@inproceedings{druskat_corpus-tools.org:_2016,
	address = {Portorož, Slovenia},
	title = {corpus-tools.org: {An} {Interoperable} {Generic} {Software} {Tool} {Set} for {Multi}-layer {Linguistic} {Corpora}},
	copyright = {All rights reserved},
	isbn = {978-2-9517408-9-1},
	url = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/918_Paper.pdf},
	language = {english},
	booktitle = {Proceedings of the {Tenth} {International} {Conference} on {Language} {Resources} and {Evaluation} ({LREC} 2016)},
	publisher = {European Language Resources Association (ELRA)},
	author = {Druskat, Stephan and Gast, Volker and Krause, Thomas and Zipser, Florian},
	editor = {Chair), Nicoletta Calzolari (Conference 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},
	year = {2016},
}

@inproceedings{druskat_workflow_2016,
	title = {A workflow for creating, analysing, and storing multi-layer corpora: {Pepper}, {Atomic}, {ANNIS} and {LAUDATIO}},
	copyright = {All rights reserved},
	doi = {10.5281/zenodo.47345},
	booktitle = {{DGfS}-{CL} {Poster} {Session}. 38. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft} ({DGfS})},
	author = {Druskat, Stephan and Krause, Thomas and Odebrecht, Carolin and Zipser, Florian},
	year = {2016},
}

@misc{zipser_saltnpepper_2015,
	address = {Berlin},
	type = {Poster},
	title = {{SaltNPepper}, {ANNIS} \& {Atomic}: {Eine} {Infrastruktur} für {Mehrebenenkorpora}},
	copyright = {All rights reserved},
	url = {http://dx.doi.org/10.5281/zenodo.20714},
	author = {Zipser, Florian and Röhrig, André and Lüdeling, Anke and Klotz, Martin and Krause, Thomas and Druskat, Stephan and Voigt, Vivian},
	year = {2015},
	note = {Digital Humanities Tag an der Humboldt Universität (DH Tag)},
}

@inproceedings{zipser_interactive_2015,
	title = {Interactive analysis of multi-layer linguistic corpora with {ANNIS}},
	copyright = {All rights reserved},
	url = {http://dx.doi.org/10.5281/zenodo.16663},
	doi = {10.5281/zenodo.16663},
	booktitle = {{DGfS}-{CL} {Poster} {Session}. 37. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft} ({DGfS})},
	author = {Zipser, Florian and Krause, Thomas and Neumann, Arne},
	month = apr,
	year = {2015},
}

@inproceedings{zipser_annis_2015,
	address = {Berlin},
	title = {{ANNIS}, {SaltNPepper} \& {PAULA}: {A} multilayer corpus infrastructure},
	copyright = {All rights reserved},
	url = {http://dx.doi.org/10.5281/zenodo.20713},
	doi = {10.5281/zenodo.20713},
	booktitle = {Final {Conference} of the {SFB} 632 {Information} {Structure}: {Advances} in {Information} {Structure} {Research} 2003 - 2015},
	author = {Zipser, Florian and Krause, Thomas and Lüdeling, Anke and Neumann, Arne and Stede, Manfred and Zeldes, Amir},
	year = {2015},
}

@inproceedings{odebrecht_austausch_2015,
	address = {Universität Leipzig},
	title = {Austausch von historischen {Texten} verschiedener {Sprachen} über das {LAUDATIO}-{Repository}},
	copyright = {All rights reserved},
	booktitle = {{DGfS}-{CL} {Poster} {Session}. 37. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft} ({DGfS})},
	author = {Odebrecht, Carolin and Krause, Thomas and Lüdeling, Anke},
	year = {2015},
}

@inproceedings{krause_laudatio._2015,
	address = {Hamburg},
	title = {{LAUDATIO}. {Ein} flexibles {Repositorium} für historische {Textdaten}},
	copyright = {All rights reserved},
	url = {https://www.gwiss.uni-hamburg.de/gwin/ueber-uns/forge2015/forge2015abstracts.pdf},
	booktitle = {Forschungsdaten in den {Geisteswissenschaften} ({FORGE} 2015)},
	publisher = {Universität Hamburg},
	author = {Krause, Thomas and Lüdeling, Anke and Odebrecht, Carolin and Zielke, Dennis},
	year = {2015},
}

@inproceedings{krause_laudatio-repository:_2014,
	title = {{LAUDATIO}-{Repository}: {Accessing} a heterogeneous field of linguistic corpora with the help of an open access repository},
	copyright = {All rights reserved},
	url = {http://dharchive.org/paper/DH2014/Poster-34.xml},
	booktitle = {Digital {Humanities} 2014 {Conference}. {Poster} {Session}},
	author = {Krause, Thomas and Lüdeling, Anke and Odebrecht, Carolin and Romary, Laurent and Schirmbacher, Peter and Zielke, Dennis},
	year = {2014},
}

@inproceedings{odebrecht_wissenschaftliche_2014,
	address = {Marburg},
	title = {Wissenschaftliche {Nutzung} der korpuslinguistischen {Infrastruktur} {LAUDATIO}},
	copyright = {All rights reserved},
	booktitle = {36. {Jahrestagung} der {DGfS}, {Poster}-{Session} der {Sektion} {Computerlinguistik}},
	author = {Odebrecht, Carolin and Zielke, Dennis and Krause, Thomas and Weißenfels, Benjamin and Belz, Malte and Schernikau, Tino and Voigt, Vivian},
	year = {2014},
}

@inproceedings{krause_annis3:_2014,
	address = {Marburg},
	title = {{ANNIS3}: {Towards} {Generic} {Corpus} {Search} and {Visualization}},
	copyright = {All rights reserved},
	booktitle = {36. {Jahrestagung} der {DGfS}, {Poster}-{Session} der {Sektion} {Computerlinguistik}},
	author = {Krause, Thomas and Weißenfels, Benjamin and Zeldes, Amir and Zipser, Florian},
	year = {2014},
}

@inproceedings{krause_langfristiger_2014,
	address = {Berlin},
	title = {Langfristiger {Zugang} und wissenschaftliche {Nutzung} historischer {Korpora} mit der korpuslinguistischen {Infrastruktur} {LAUDATIO}},
	copyright = {All rights reserved},
	url = {http://www.fu-berlin.de/sites/open_access/Veranstaltungen/oa_berlin/poster/LAUDATIO_Krause-Thomas-Odebrecht-Carolin-Zielke-Dennis_HU-Berlin.pdf?1412841033},
	booktitle = {Open-{Access}-{Strategie} für {Berlin}},
	publisher = {Freie Universität zu Berlin},
	author = {Krause, Thomas and Odebrecht, Carolin and Zielke, Dennis},
	year = {2014},
}

@misc{krause_unary_2013,
	address = {Sapienza Università di Roma},
	title = {Unary {TEI} {Elements} and the {Token} {Based} {Corpus}},
	copyright = {All rights reserved},
	url = {https://tei-c.org/Vault/MembersMeetings/2013/wp-content/uploads/2013/09/Krause_etal.pdf},
	author = {Krause, Thomas and Odebrecht, Carolin and Zeldes, Amir and Zipser, Florian},
	month = oct,
	year = {2013},
	note = {Workshop Perspectives on Querying TEI-annotated data, TEI Conference 2013},
}

@misc{odebrecht_metadata_2013,
	title = {Metadata in an {Infrastructure} for {Historical} {Corpora}.},
	copyright = {All rights reserved},
	author = {Odebrecht, Carolin and Krause, Thomas},
	year = {2013},
	note = {Published: SFB 732 Incremental Specification in Context. Kolloquium. Stuttgart},
}

@inproceedings{krause_wie_2013,
	address = {Universität Potsdam},
	title = {Wie kann der {Zugriff}, die {Wiederverwendung} und langfristige {Speicherung} von linguistischen {Korpora} realisiert werden?},
	copyright = {All rights reserved},
	url = {https://www.linguistik.hu-berlin.de/institut/professuren/korpuslinguistik/mitarbeiter-innen/carolin/dgfs2013-krause-odebrecht-zielke},
	booktitle = {35. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft} ({DGfS})},
	author = {Krause, Thomas and Odebrecht, Carolin and Zielke, Dennis},
	year = {2013},
}

@inproceedings{krause_multiple_2012,
	address = {Universitetet i Oslo},
	title = {Multiple {Tokenization} in a {Diachronic} {Corpus}},
	copyright = {All rights reserved},
	url = {http://www.hf.uio.no/ifikk/english/research/projects/proiel/ealc/abstracts/Krause_et_al.pdf},
	booktitle = {Exploring {Ancient} {Languages} through {Corpora} {Conference} ({EALC})},
	author = {Krause, Thomas and Lüdeling, Anke and Odebrecht, Carolin and Zeldes, Amir},
	year = {2012},
}

@inproceedings{krause_topological_2011,
	address = {Hamburg},
	title = {Topological {Fields}, {Constituents} and {Coreference}: {A} {New} {Multi}-layer {Architecture} for {TüBa}-{D}/{Z}.},
	copyright = {All rights reserved},
	url = {http://exmaralda.org/gscl2011/downloads/AZM96.pdf},
	booktitle = {Proceedings of the {Conference} of the  {German} {Society} for {Computational} {Linguistics} and  {Language} {Technology} ({GSCL}) 2011},
	author = {Krause, Thomas and Ritz, Julia and Zeldes, Amir and Zipser, Florian},
	year = {2011},
	pages = {259--262},
}

@mastersthesis{krause_erfahrungsbasierte_2011,
	title = {Erfahrungsbasierte {Lernmethoden} zur visuellen {Trajektorienvorhersage} humanoider {Roboter}},
	copyright = {All rights reserved},
	url = {https://www.linguistik.hu-berlin.de/institut/professuren/korpuslinguistik/mitarbeiter-innen/thomas/publications/verhalten_nao.pdf},
	school = {Humboldt-Universität zu Berlin},
	author = {Krause, Thomas},
	year = {2011},
}

@techreport{burkhard_nao-team_2010,
	title = {{NAO}-{Team} {Humboldt} 2010},
	url = {http://www.naoteamhumboldt.de/wp-content/uploads/2010/02/NaoTH10Description.pdf},
	institution = {Humboldt Universität zu Berlin},
	author = {Burkhard, Hans-Dieter and Holzhauer, Florian and Krause, Thomas and Mellmann, Heinrich and Ritter, Claas Norman and Welter, Oliver and Xu, Yuan},
	year = {2010},
}

@inproceedings{reznicek_dass_2010,
	address = {Berlin},
	title = {"{Dass} wenn man etwas will, muss man dafür arbeiten"- {Zielhypothesen} im {Lernerkorpus} {Falko}},
	copyright = {All rights reserved},
	booktitle = {31. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft}},
	author = {Reznicek, Marc and Krummes, Cedric and Hirschmann, Hagen and Lüdeling, Anke and Ensslin, Astrid and Chan, Jia Wei and Krause, Amir Zeldes Thomas and Zipser, Florian},
	year = {2010},
}

@inproceedings{mellmann_naoth_2010,
	address = {Darmstadt},
	title = {{NaoTH} {Software} {Architecture} for an {Autonomous} {Agent}},
	url = {http://www.naoteamhumboldt.de/wp-content/papercite-data/pdf/scpr-mellmannxuetal-10.pdf},
	abstract = {An appropriate architecture (i.e., framework) is the base of each successful heterogeneous software project. It enables a group of developers to work at the same project and to organize their solutions. From this point of view, the artificial intelligence and/or robotics related research projects are usually more complicated, since the actual result of the project is often not clear. In particular, a strong organization of the software is necessary if the project is involved in education. Obviously, there is no perfect framework which could satisfy all the needs of the developers. In this paper we present a modular software architecture designed to implement an autonomous agent. In particular, it is used to develop software which is used simultaneously at several platforms (e.g., humanoid robot, simulated agent). One of the main aspects considered in our design is a strong code modularization which allows for re-usability, transparency and easily testing. Other important aspects are real-time applicability and simple usage. This paper presents the main concepts and the particular implementation of the important parts. We also provide a qualitative comparison with other existing robotics frameworks.},
	booktitle = {Proceedings of the {International} {Workshop} on {Standards} and {Common} {Platforms} for {Robotics} ({SCPR} 2010)},
	author = {Mellmann, Heinrich and Xu, Yuan and Krause, Thomas and Holzhauer, Florian},
	month = nov,
	year = {2010},
	pages = {316--327},
}

An appropriate architecture (i.e., framework) is the base of each successful heterogeneous software project. It enables a group of developers to work at the same project and to organize their solutions. From this point of view, the artificial intelligence and/or robotics related research projects are usually more complicated, since the actual result of the project is often not clear. In particular, a strong organization of the software is necessary if the project is involved in education. Obviously, there is no perfect framework which could satisfy all the needs of the developers. In this paper we present a modular software architecture designed to implement an autonomous agent. In particular, it is used to develop software which is used simultaneously at several platforms (e.g., humanoid robot, simulated agent). One of the main aspects considered in our design is a strong code modularization which allows for re-usability, transparency and easily testing. Other important aspects are real-time applicability and simple usage. This paper presents the main concepts and the particular implementation of the important parts. We also provide a qualitative comparison with other existing robotics frameworks.

@techreport{burkhard_nao-team_2009,
	title = {{NAO}-{Team} {Humboldt} 2009},
	url = {http://www.naoteamhumboldt.de/wp-content/uploads/2010/02/NaoTH09Report_final.pdf},
	institution = {Humboldt Universität zu Berlin},
	author = {Burkhard, Hans-Dieter and Holzhauer, Florian and Krause, Thomas and Mellmann, Heinrich and Ritter, Claas Norman and Welter, Oliver and Xu, Yuan},
	year = {2009},
}

@inproceedings{chiarcos_search_2009,
	address = {Osnabrück},
	title = {Search and {Visualization} of {Richly} {Annotated} {Corpora} with {ANNIS2}},
	copyright = {All rights reserved},
	url = {https://www.linguistik.hu-berlin.de/institut/professuren/korpuslinguistik/mitarbeiter-innen/amir/pdf/DGfS09_annis_poster},
	booktitle = {31. {Jahrestagung} der {Deutschen} {Gesellschaft} für {Sprachwissenschaft}},
	author = {Chiarcos, Christian and Krause, Thomas and Lüdeling, Anke and Ritz, Julia and Rosenfeld, Viktor and Stede, Manfred and Zeldes, Amir and Zipser, Florian},
	year = {2009},
}

@techreport{rofer_germanteam_2005,
	title = {{GermanTeam} 2005},
	url = {http://web.archive.org/web/20110415023802/http://www.germanteam.org/GT2005.pdf},
	author = {Röfer, Thomas and Laue, Tim and Weber, Michael and Burkhard, Hans-Dieter and Jüngel, Matthias and Göhring, Daniel and Hoffmann, Jan and Altmeyer, Benjamin and Krause, Thomas and Spranger, Michael and Stryk, Oskar von and Brunn, Ronnie and Dassler, Marc and Kunz, Michael and Oberlies, Tobias and Risler, Max and Schwiegelshohn, Uwe and Hebbel, Matthias and Nisticó, Walter and Czarnetzki, Stefan and Kerkhof, Thorsten and Meyer, Matthias and Rohde, Carsten and Schmitz, Bastian and Wachter, Michael and Wegner, Tobias and Zarges, Christine},
	year = {2005},
}

@incollection{UyanikEtAl2023,
	title = {Differenzierung und {Standardisierung}. {Zur} {Entwicklung} von {Registern}},
	booktitle = {Historische {Fach}- und {Wissenschaftstexte} kontrastiv},
	author = {Uyanık, Esra and Müller, Sven Oliver and Lüdeling, Anke and Krause, Thomas},
	editor = {Pawłowski, Grzegorz and Guławska, Małgorzata and Bąk, Paweł},
}