Dr. Tolga Uslu

@inproceedings{Mehler:Uslu:Baumartz:2021,
  author    = {Mehler, Alexander and Baumartz, Daniel and Uslu, Tolga},
  title     = {{SemioGraphs:} Visualizing Topic Networks as Mulit-Codal Graphs},
  booktitle = {International Quantitative Linguistics Conference (QUALICO 2021)},
  series    = {QUALICO 2021},
  location  = {Tokyo, Japan},
  year      = {2021},
  poster    = {https://www.texttechnologylab.org/files/Qualico_2021_Semiograph_Poster.pdf}
}

@article{Luecking:Brueckner:Abrami:Uslu:Mehler:2021,
  journal   = {Frontiers in Education},
  doi       = {10.3389/feduc.2020.578475},
  title     = {Computational linguistic assessment of textbooks and online texts
               by means of threshold concepts in economics},
  author    = {L{\"u}cking, Andy and Br{\"u}ckner, Sebastian and Abrami, Giuseppe
               and Uslu, Tolga and Mehler, Alexander},
  eid       = {578475},
  url       = {https://www.frontiersin.org/articles/10.3389/feduc.2020.578475/},
  year      = {2021}
}

@phdthesis{Uslu:2020,
  author    = {Tolga Uslu},
  title     = {Multi-document analysis : semantic analysis of large text corpora
               beyond topic modeling},
  pages     = {204},
  year      = {2020},
  url       = {http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56140},
  pdf       = {http://publikationen.ub.uni-frankfurt.de/files/56140/Dissertation_Tolga_Uslu.pdf}
}

@article{Mehler:Hemati:Welke:Konca:Uslu:2020,
  abstract  = {We test the hypothesis that the extent to which one obtains information
               on a given topic through Wikipedia depends on the language in
               which it is consulted. Controlling the size factor, we investigate
               this hypothesis for a number of 25 subject areas. Since Wikipedia
               is a central part of the web-based information landscape, this
               indicates a language-related, linguistic bias. The article therefore
               deals with the question of whether Wikipedia exhibits this kind
               of linguistic relativity or not. From the perspective of educational
               science, the article develops a computational model of the information
               landscape from which multiple texts are drawn as typical input
               of web-based reading. For this purpose, it develops a hybrid model
               of intra- and intertextual similarity of different parts of the
               information landscape and tests this model on the example of 35
               languages and corresponding Wikipedias. In the way it measures
               the similarities of hypertexts, the article goes beyond existing
               approaches by examining their structural and semantic aspects
               intra- and intertextually. In this way it builds a bridge between
               reading research, educational science, Wikipedia research and
               computational linguistics.},
  author    = {Mehler, Alexander and Hemati, Wahed and Welke, Pascal and Konca, Maxim
               and Uslu, Tolga},
  doi       = {10.3389/feduc.2020.562670},
  issn      = {2504-284X},
  journal   = {Frontiers in Education},
  pages     = {206},
  title     = {Multiple Texts as a Limiting Factor in Online Learning: Quantifying
               (Dis-)similarities of Knowledge Networks},
  url       = {https://www.frontiersin.org/article/10.3389/feduc.2020.562670},
  pdf       = {https://www.frontiersin.org/articles/10.3389/feduc.2020.562670/pdf},
  volume    = {5},
  year      = {2020}
}

@article{Luecking:et:al:2020,
  author    = {Andy L{\"{u}}cking and Sebastian Br{\"{u}}ckner and Giuseppe Abrami
               and Tolga Uslu and Alexander Mehler},
  title     = {Computational linguistic assessment of textbook and online learning
               media by means of threshold concepts in business education},
  journal   = {CoRR},
  volume    = {abs/2008.02096},
  year      = {2020},
  url       = {https://arxiv.org/abs/2008.02096},
  archiveprefix = {arXiv},
  eprint    = {2008.02096},
  timestamp = {Fri, 07 Aug 2020 15:07:21 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2008-02096.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{Mehler:et:al:2020b,
  author    = {Mehler, Alexander and Jussen, Bernhard and Geelhaar, Tim and Henlein, Alexander
               and Abrami, Giuseppe and Baumartz, Daniel and Uslu, Tolga and Hemati, Wahed},
  title     = {{The Frankfurt Latin Lexicon. From Morphological Expansion and
               Word Embeddings to SemioGraphs}},
  journal   = {Studi e Saggi Linguistici},
  doi       = {10.4454/ssl.v58i1.276},
  year      = {2020},
  volume    = {58},
  number    = {1},
  pages     = {121--155},
  abstract  = {In this article we present the Frankfurt Latin Lexicon (FLL),
               a lexical resource for Medieval Latin that is used both for the
               lemmatization of Latin texts and for the post-editing of lemmatizations.
               We describe recent advances in the development of lemmatizers
               and test them against the Capitularies corpus (comprising Frankish
               royal edicts, mid-6th to mid-9th century), a corpus created as
               a reference for processing Medieval Latin. We also consider the
               post-correction of lemmatizations using a limited crowdsourcing
               process aimed at continuous review and updating of the FLL. Starting
               from the texts resulting from this lemmatization process, we describe
               the extension of the FLL by means of word embeddings, whose interactive
               traversing by means of SemioGraphs completes the digital enhanced
               hermeneutic circle. In this way, the article argues for a more
               comprehensive understanding of lemmatization, encompassing classical
               machine learning as well as intellectual post-corrections and,
               in particular, human computation in the form of interpretation
               processes based on graph representations of the underlying lexical
               resources.},
  url       = {https://www.studiesaggilinguistici.it/index.php/ssl/article/view/276},
  pdf       = {https://www.studiesaggilinguistici.it/index.php/ssl/article/download/276/219}
}

@article{Mehler:Gleim:Gaitsch:Uslu:Hemati:2020,
  author    = {Alexander Mehler and R{\"{u}}diger Gleim and Regina Gaitsch and Tolga Uslu
               and Wahed Hemati},
  title     = {From Topic Networks to Distributed Cognitive Maps: {Zipfian} Topic
               Universes in the Area of Volunteered Geographic Information},
  journal   = {Complexity},
  volume    = {4},
  doi       = {10.1155/2020/4607025},
  pages     = {1-47},
  issuetitle = {Cognitive Network Science: A New Frontier},
  year      = {2020}
}

@inproceedings{Uslu:Mehler:Baumartz:2019,
  author    = {Uslu, Tolga and Mehler, Alexander and Baumartz, Daniel},
  booktitle = {{Proceedings of the 20th International Conference on Computational
               Linguistics and Intelligent Text Processing, (CICLing 2019)}},
  location  = {La Rochelle, France},
  series    = {{CICLing 2019}},
  title     = {{Computing Classifier-based Embeddings with the Help of text2ddc}},
  year      = {2019}
}

@inproceedings{Uslu:Mehler:Schulz:Baumartz:2019,
  author    = {Uslu, Tolga and Mehler, Alexander and Schulz, Clemens and Baumartz, Daniel},
  booktitle = {{Proceedings of the Digital Humanities 2019, (DH2019)}},
  location  = {Utrecht, Netherlands},
  series    = {{DH2019}},
  title     = {{{BigSense}: a Word Sense Disambiguator for Big Data}},
  year      = {2019},
  url       = {https://dev.clariah.nl/files/dh2019/boa/0199.html}
}

@inproceedings{Mehler:Uslu:Gleim:Baumartz:2019,
  author    = {Mehler, Alexander and Uslu, Tolga and Gleim, Rüdiger and Baumartz, Daniel},
  title     = {{text2ddc meets Literature - Ein Verfahren für die Analyse und
               Visualisierung thematischer Makrostrukturen}},
  booktitle = {Proceedings of the 6th Digital Humanities Conference in the German-speaking
               Countries, DHd 2019},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/DHD_Poster___text2ddc_meets_Literature_Poster.pdf},
  series    = {DHd 2019},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/Preprint_DHd2019_text2ddc_meets_Literature.pdf},
  location  = {Frankfurt, Germany},
  year      = {2019}
}

@inproceedings{Hemati:Mehler:Uslu:Abrami:2019,
  author    = {Hemati, Wahed and Mehler, Alexander and Uslu, Tolga and Abrami, Giuseppe},
  title     = {{Der TextImager als Front- und Backend für das verteilte NLP von
               Big Digital Humanities Data}},
  booktitle = {Proceedings of the 6th Digital Humanities Conference in the German-speaking
               Countries, DHd 2019},
  series    = {DHd 2019},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/Der-TextImager-als-Fron-und-Backend.pdf},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/DHD19_TextImager.pdf},
  location  = {Frankfurt, Germany},
  year      = {2019}
}

@article{Gleim:Eger:Mehler:2019,
  author    = {Gleim, R\"{u}diger and Eger, Steffen and Mehler, Alexander and Uslu, Tolga
               and Hemati, Wahed and L\"{u}cking, Andy and Henlein, Alexander and Kahlsdorf, Sven
               and Hoenen, Armin},
  title     = {A practitioner's view: a survey and comparison of lemmatization
               and morphological tagging in German and Latin},
  journal   = {Journal of Language Modeling},
  year      = {2019},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2019/07/jlm-tagging.pdf},
  doi       = {10.15398/jlm.v7i1.205},
  url       = {http://jlm.ipipan.waw.pl/index.php/JLM/article/view/205}
}

@inproceedings{Uslu:Mehler:2018,
  author    = {Tolga Uslu and Alexander Mehler},
  title     = {{PolyViz}: a Visualization System for a Special Kind of Multipartite Graphs},
  booktitle = {Proceedings of the IEEE VIS 2018},
  series    = {IEEE VIS 2018},
  location  = {Berlin, Germany},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/07/polyviz-visualization-system.pdf},
  year      = {2018}
}

@inproceedings{Baumartz:Uslu:Mehler:2018,
  author    = {Daniel Baumartz and Tolga Uslu and Alexander Mehler},
  title     = {{LTV}: Labeled Topic Vector},
  booktitle = {Proceedings of {COLING 2018}, the 27th International Conference
               on Computational Linguistics: System Demonstrations, August 20-26},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {The COLING 2018 Organizing Committee},
  abstract  = {In this paper, we present LTV, a website and an API that generate
               labeled topic classifications based on the Dewey Decimal Classification
               (DDC), an international standard for topic classification in libraries.
               We introduce nnDDC, a largely language-independent neural network-based
               classifier for DDC-related topic classification, which we optimized
               using a wide range of linguistic features to achieve an F-score
               of 87.4\%. To show that our approach is language-independent,
               we evaluate nnDDC using up to 40 different languages. We derive
               a topic model based on nnDDC, which generates probability distributions
               over semantic units for any input on sense-, word- and text-level.
               Unlike related approaches, however, these probabilities are estimated
               by means of nnDDC so that each dimension of the resulting vector
               representation is uniquely labeled by a DDC class. In this way,
               we introduce a neural network-based Classifier-Induced Semantic
               Space (nnCISS).},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/06/coling2018.pdf}
}

@article{Driller:et:al:2018,
  author    = {Christine Driller and Markus Koch and Marco Schmidt and Claus Weiland
               and Thomas Hörnschemeyer and Thomas Hickler and Giuseppe Abrami and Sajawel Ahmed
               and Rüdiger Gleim and Wahed Hemati and Tolga Uslu and Alexander Mehler
               and Adrian Pachzelt and Jashar Rexhepi and Thomas Risse and Janina Schuster
               and Gerwin Kasperek and Angela Hausinger},
  title     = {Workflow and Current Achievements of BIOfid, an Information Service
               Mobilizing Biodiversity Data from Literature Sources},
  volume    = {2},
  number    = {},
  year      = {2018},
  doi       = {10.3897/biss.2.25876},
  publisher = {Pensoft Publishers},
  abstract  = {BIOfid is a specialized information service currently being developed
               to mobilize biodiversity data dormant in printed historical and
               modern literature and to offer a platform for open access journals
               on the science of biodiversity. Our team of librarians, computer
               scientists and biologists produce high-quality text digitizations,
               develop new text-mining tools and generate detailed ontologies
               enabling semantic text analysis and semantic search by means of
               user-specific queries. In a pilot project we focus on German publications
               on the distribution and ecology of vascular plants, birds, moths
               and butterflies extending back to the Linnaeus period about 250
               years ago. The three organism groups have been selected according
               to current demands of the relevant research community in Germany.
               The text corpus defined for this purpose comprises over 400 volumes
               with more than 100,000 pages to be digitized and will be complemented
               by journals from other digitization projects, copyright-free and
               project-related literature. With TextImager (Natural Language
               Processing & Text Visualization) and TextAnnotator (Discourse
               Semantic Annotation) we have already extended and launched tools
               that focus on the text-analytical section of our project. Furthermore,
               taxonomic and anatomical ontologies elaborated by us for the taxa
               prioritized by the project’s target group - German institutions
               and scientists active in biodiversity research - are constantly
               improved and expanded to maximize scientific data output. Our
               poster describes the general workflow of our project ranging from
               literature acquisition via software development, to data availability
               on the BIOfid web portal (http://biofid.de/), and the implementation
               into existing platforms which serve to promote global accessibility
               of biodiversity data.},
  issn      = {},
  pages     = {e25876},
  url       = {https://doi.org/10.3897/biss.2.25876},
  eprint    = {https://doi.org/10.3897/biss.2.25876},
  journal   = {Biodiversity Information Science and Standards},
  keywords  = {biofid}
}

@inproceedings{Hemati:Mehler:Uslu:Baumartz:Abrami:2018,
  author    = {Wahed Hemati and Alexander Mehler and Tolga Uslu and Daniel Baumartz
               and Giuseppe Abrami},
  title     = {Evaluating and Integrating Databases in the Area of {NLP}},
  booktitle = {International Quantitative Linguistics Conference (QUALICO 2018)},
  year      = {2018},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/04/Hemat-Mehler-Uslu-Baumartz-Abrami-Qualico-2018.pdf},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2018/10/qualico2018_databases_poster_hemati_mehler_uslu_baumartz_abrami.pdf},
  location  = {Wroclaw, Poland}
}

@incollection{Mehler:Hemati:Uslu:Luecking:2018,
  author    = {Alexander Mehler and Wahed Hemati and Tolga Uslu and Andy Lücking},
  title     = {A Multidimensional Model of Syntactic Dependency Trees for Authorship
               Attribution},
  booktitle = {Quantitative analysis of dependency structures},
  publisher = {De Gruyter},
  editor    = {Jingyang Jiang and Haitao Liu},
  address   = {Berlin/New York},
  abstract  = {Abstract: In this chapter we introduce a multidimensional model
               of syntactic dependency trees. Our ultimate goal is to generate
               fingerprints of such trees to predict the author of the underlying
               sentences. The chapter makes a first attempt to create such fingerprints
               for sentence categorization via the detour of text categorization.
               We show that at text level, aggregated dependency structures actually
               provide information about authorship. At the same time, we show
               that this does not hold for topic detection. We evaluate our model
               using a quarter of a million sentences collected in two corpora:
               the first is sampled from literary texts, the second from Wikipedia
               articles. As a second finding of our approach, we show that quantitative
               models of dependency structure do not yet allow for detecting
               syntactic alignment in written communication. We conclude that
               this is mainly due to effects of lexical alignment on syntactic
               alignment.},
  keywords  = {Dependency structure, Authorship attribution, Text
                   categorization, Syntactic Alignment},
  year      = {2018}
}

@inproceedings{Uslu:Mehler:Meyer:2018,
  author    = {Tolga Uslu and Alexander Mehler and Dirk Meyer},
  title     = {{{LitViz}: Visualizing Literary Data by Means of text2voronoi}},
  booktitle = {Proceedings of the Digital Humanities 2018},
  series    = {DH2018},
  location  = {Mexico City, Mexico},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/LitViz.pdf},
  year      = {2018}
}

@inproceedings{Uslu:et:al:2018:a,
  author    = {Tolga Uslu and Lisa Miebach and Steffen Wolfsgruber and Michael Wagner
               and Klaus Fließbach and Rüdiger Gleim and Wahed Hemati and Alexander Henlein
               and Alexander Mehler},
  title     = {{Automatic Classification in Memory Clinic Patients and in Depressive Patients}},
  booktitle = {Proceedings of Resources and ProcessIng of linguistic, para-linguistic
               and extra-linguistic Data from people with various forms of cognitive/psychiatric
               impairments (RaPID-2)},
  series    = {RaPID},
  location  = {Miyazaki, Japan},
  year      = {2018}
}

@article{Mehler:Gleim:Luecking:Uslu:Stegbauer:2018,
  author    = {Alexander Mehler and Rüdiger Gleim and Andy Lücking and Tolga Uslu
               and Christian Stegbauer},
  title     = {On the Self-similarity of {Wikipedia} Talks: a Combined Discourse-analytical
               and Quantitative Approach},
  journal   = {Glottometrics},
  volume    = {40},
  pages     = {1-44},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/Glottometrics-Mehler.pdf},
  year      = {2018}
}

@inproceedings{Uslu:Mehler:Niekler:Baumartz:2018,
  author    = {Tolga Uslu and Alexander Mehler and Andreas Niekler and Daniel Baumartz},
  title     = {Towards a {DDC}-based Topic Network Model of Wikipedia},
  booktitle = {Proceedings of 2nd International Workshop on Modeling, Analysis,
               and Management of Social Networks and their Applications (SOCNET
               2018), February 28, 2018},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TowardsDDC.pdf},
  year      = {2018}
}

@inproceedings{Uslu:et:al:2018,
  author    = {Tolga Uslu and Alexander Mehler and Daniel Baumartz and Alexander Henlein
               and Wahed Hemati},
  title     = {fastSense: An Efficient Word Sense Disambiguation Classifier},
  booktitle = {Proceedings of the 11th edition of the Language Resources and
               Evaluation Conference, May 7 - 12},
  series    = {LREC 2018},
  address   = {Miyazaki, Japan},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/fastSense.pdf},
  year      = {2018}
}

@inproceedings{Hemati:Mehler:Uslu:2017,
  author    = {Wahed Hemati and Alexander Mehler and Tolga Uslu},
  title     = {{CRFVoter}: Chemical Entity Mention, Gene and Protein Related
               Object recognition using a conglomerate of CRF based tools},
  booktitle = {BioCreative V.5. Proceedings},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/CRFVoter.pdf},
  year      = {2017}
}

@inproceedings{Hemati:Uslu:Mehler:2017,
  author    = {Wahed Hemati and Tolga Uslu and Alexander Mehler},
  title     = {{TextImager} as an interface to {BeCalm}},
  booktitle = {BioCreative V.5. Proceedings},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager_BeCalm.pdf},
  year      = {2017}
}

@inproceedings{Mehler:Gleim:Hemati:Uslu:2017,
  author    = {Alexander Mehler and Rüdiger Gleim and Wahed Hemati and Tolga Uslu},
  title     = {{Skalenfreie online soziale Lexika am Beispiel von Wiktionary}},
  booktitle = {Proceedings of 53rd Annual Conference of the Institut für Deutsche
               Sprache (IDS), March 14-16, Mannheim, Germany},
  editor    = {Stefan Engelberg and Henning Lobin and Kathrin Steyer and Sascha Wolfer},
  address   = {Berlin},
  publisher = {De Gruyter},
  note      = {In German. Title translates into: Scale-free
                   online-social Lexika by Example of Wiktionary},
  abstract  = {In English: The paper deals with characteristics of the structural,
               thematic and participatory dynamics of collaboratively generated
               lexical networks. This is done by example of Wiktionary. Starting
               from a network-theoretical model in terms of so-called multi-layer
               networks, we describe Wiktionary as a scale-free lexicon. Systems
               of this sort are characterized by the fact that their content-related
               dynamics is determined by the underlying dynamics of collaborating
               authors. This happens in a way that social structure imprints
               on content structure. According to this conception, the unequal
               distribution of the activities of authors results in a correspondingly
               unequal distribution of the information units documented within
               the lexicon. The paper focuses on foundations for describing such
               systems starting from a parameter space which requires to deal
               with Wiktionary as an issue in big data analysis. In German: Der
               Beitrag thematisiert Eigenschaften der strukturellen, thematischen
               und partizipativen Dynamik kollaborativ erzeugter lexikalischer
               Netzwerke am Beispiel von Wiktionary. Ausgehend von einem netzwerktheoretischen
               Modell in Form so genannter Mehrebenennetzwerke wird Wiktionary
               als ein skalenfreies Lexikon beschrieben. Systeme dieser Art zeichnen
               sich dadurch aus, dass ihre inhaltliche Dynamik durch die zugrundeliegende
               Kollaborationsdynamik bestimmt wird, und zwar so, dass sich die
               soziale Struktur der entsprechenden inhaltlichen Struktur aufprägt.
               Dieser Auffassung gemäß führt die Ungleichverteilung der Aktivitäten
               von Lexikonproduzenten zu einer analogen Ungleichverteilung der
               im Lexikon dokumentierten Informationseinheiten. Der Beitrag thematisiert
               Grundlagen zur Beschreibung solcher Systeme ausgehend von einem
               Parameterraum, welcher die netzwerkanalytische Betrachtung von
               Wiktionary als Big-Data-Problem darstellt.},
  year      = {2017}
}

@inproceedings{Uslu:Hemati:Mehler:Baumartz:2017,
  author    = {Tolga Uslu and Wahed Hemati and Alexander Mehler and Daniel Baumartz},
  title     = {{TextImager} as a Generic Interface to {R}},
  booktitle = {Software Demonstrations of the 15th Conference of the European
               Chapter of the Association for Computational Linguistics (EACL
               2017)},
  location  = {Valencia, Spain},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager.pdf},
  year      = {2017}
}

@inproceedings{Hemati:Uslu:Mehler:2016,
  author    = {Wahed Hemati and Tolga Uslu and Alexander Mehler},
  title     = {TextImager: a Distributed UIMA-based System for NLP},
  booktitle = {Proceedings of the COLING 2016 System Demonstrations},
  organization = {Federated Conference on Computer Science and
                   Information Systems},
  location  = {Osaka, Japan},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager2016.pdf},
  year      = {2016}
}

@inproceedings{Mehler:Uslu:Hemati:2016,
  author    = {Alexander Mehler and Tolga Uslu and Wahed Hemati},
  title     = {Text2voronoi: An Image-driven Approach to Differential Diagnosis},
  booktitle = {Proceedings of the 5th Workshop on Vision and Language (VL'16)
               hosted by the 54th Annual Meeting of the Association for Computational
               Linguistics (ACL), Berlin},
  pdf       = {https://aclweb.org/anthology/W/W16/W16-3212.pdf},
  year      = {2016}
}

@article{Mehler:et:al:2016,
  author    = {Alexander Mehler and Rüdiger Gleim and Tim vor der Brück and Wahed Hemati
               and Tolga Uslu and Steffen Eger},
  title     = {Wikidition: Automatic Lexiconization and Linkification of Text Corpora},
  journal   = {Information Technology},
  volume    = {58},
  pages     = {70-79},
  abstract  = {We introduce a new text technology, called Wikidition, which automatically
               generates large scale editions of corpora of natural language
               texts. Wikidition combines a wide range of text mining tools for
               automatically linking lexical, sentential and textual units. This
               includes the extraction of corpus-specific lexica down to the
               level of syntactic words and their grammatical categories. To
               this end, we introduce a novel measure of text reuse and exemplify
               Wikidition by means of the capitularies, that is, a corpus of
               Medieval Latin texts.},
  doi       = {10.1515/itit-2015-0035},
  year      = {2016}
}