@book{molz2020, title = {A Close and Distant Reading of Shakespearean Intertextuality: Towards a Mixed Method Approach for Literary Studies}, author = {Molz, Johannes}, year = 2020, publisher = {Universit{\"a}tsbibliothek Ludwig-Maximilians-Universit{\"a}t}, series = {Open Publishing in the Humanities}, doi = {10.5282/oph.4} } @article{trillini2010, title = {{A ‘key to all quotations’? A corpus-based parameter model of intertextuality}}, author = {Hohl Trillini, Regula and Quassdorf, Sixta}, year = 2010, journal = {Literary and Linguistic Computing}, number = 25, pages = {269--286}, doi = {10.1093/llc/fqq003}, issue = 3 } @book{schaum2004, title = {{I}ronie und {E}thik in {A}nnette von {D}roste-{H}ülshoffs {J}udenbuche}, author = {Konrad Schaum}, year = 2004, publisher = {Winter}, series = {Beiträge zur neueren Literaturgeschichte; [Folge 3], Bd. 204}, pages = {99--194}, chapter = {Die Judenbuche als Sittengemälde} } @article{da2019, title = {The Computational Case against Computational Literary Studies}, author = {Da, Nan Z.}, year = 2019, journal = {Critical Inquiry}, number = 45, pages = {601--639}, doi = {10.1086/702594}, issue = 3 } @article{descher2018, title = {Die Explizierung des Impliziten}, author = {Stefan Descher and Thomas Petraschka}, year = 2018, journal = {Scientia Poetica}, volume = 22, pages = {180--208}, doi = {10.1515/scipo-2018-007}, issue = 1 } @incollection{winko2015, title = {Wissen und Inferenz – Zum Verstehen und Interpretieren literarischer Texte am Beispiel von Hans Magnus Enzensbergers Gedicht Frühschriften}, author = {Simone Winko and Fotis Jannidis}, year = 2015, booktitle = {Literatur interpretieren: Interdisziplinäre Beiträge zur Theorie und Praxis}, publisher = {Brill | mentis}, pages = {221--250}, doi = {10.30965/9783957438973}, editor = {Jan Borkowski and Stefan Descher and Felicitas Ferder and Philipp David Heine} } @inproceedings{wallace2019, title = {Do {NLP} Models Know Numbers? Probing Numeracy in Embeddings}, author = {Wallace, Eric and Wang, Yizhong and Li, Sujian and Singh, Sameer and Gardner, Matt}, year = 2019, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, publisher = {Association for Computational Linguistics}, pages = {5307--5315}, doi = {10.18653/v1/D19-1534} } @misc{Wu2016, title = {Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation}, author = {Wu, Yonghui and Schuster, Mike and Chen, Zhifeng and Le, Quoc V. and Norouzi, Mohammad and Macherey, Wolfgang and Krikun, Maxim and Cao, Yuan and Gao, Qin and Macherey, Klaus and Klingner, Jeff and Shah, Apurva and Johnson, Melvin and Liu, Xiaobing and Kaiser, Łukasz and Gouws, Stephan and Kato, Yoshikiyo and Kudo, Taku and Kazawa, Hideto and Stevens, Keith and Kurian, George and Patil, Nishant and Wang, Wei and Young, Cliff and Smith, Jason and Riesa, Jason and Rudnick, Alex and Vinyals, Oriol and Corrado, Greg and Hughes, Macduff and Dean, Jeffrey}, year = 2016, publisher = {arXiv}, doi = {10.48550/ARXIV.1609.08144} } @inproceedings{brunner2020, title = {To BERT or not to BERT-Comparing Contextual Embeddings in a Deep Learning Architecture for the Automatic Recognition of four Types of Speech, Thought and Writing Representation.}, author = {Brunner, Annelen and Tu, Ngoc Duyen Tanja and Weimer, Lukas and Jannidis, Fotis}, year = 2020, booktitle = {SwissText/KONVENS}, url = {https://ceur-ws.org/Vol-2624/paper5.pdf}, urldate = {2023-11-02} } @inproceedings{elson2010, title = {Automatic Attribution of Quoted Speech in Literary Narrative}, author = {Elson, David K. and McKeown, Kathleen R.}, year = 2010, booktitle = {Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence}, location = {Atlanta, Georgia}, publisher = {AAAI Press}, series = {AAAI'10}, pages = {1013–1019}, numpages = 7 } @inproceedings{almeida2014, title = {A Joint Model for Quotation Attribution and Coreference Resolution}, author = {Almeida, Mariana S. C. and Almeida, Miguel B. and Martins, Andr{\'e} F. T.}, year = 2014, booktitle = {Proceedings of the 14th Conference of the {E}uropean Chapter of the Association for Computational Linguistics}, publisher = {Association for Computational Linguistics}, pages = {39--48}, doi = {10.3115/v1/E14-1005} } @inproceedings{pareti2013, title = {Automatically Detecting and Attributing Indirect Quotations}, author = {Pareti, Silvia and O{'}Keefe, Tim and Konstas, Ioannis and Curran, James R. and Koprinska, Irena}, year = 2013, booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing}, publisher = {Association for Computational Linguistics}, pages = {989--999}, url = {https://aclanthology.org/D13-1101}, urldate = {2023-11-02} } @inproceedings{scheible2016, title = {Model Architectures for Quotation Detection}, author = {Scheible, Christian and Klinger, Roman and Pad{\'o}, Sebastian}, year = 2016, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, publisher = {Association for Computational Linguistics}, pages = {1736--1745}, doi = {10.18653/v1/P16-1164} } @inproceedings{papay2019, title = {Quotation Detection and Classification with a Corpus-Agnostic Model}, author = {Papay, Sean and Pad{\'o}, Sebastian}, year = 2019, booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)}, publisher = {INCOMA Ltd.}, pages = {888--894}, doi = {10.26615/978-954-452-056-4_103} } @inproceedings{arnold2021, title = {{L}otte and {A}nnette: {A} {F}ramework for {F}inding and {E}xploring {K}ey {P}assages in {L}iterary {W}orks}, author = {Arnold, Frederik and J{\"a}schke, Robert}, year = 2021, booktitle = {Proceedings of the Workshop on Natural Language Processing for Digital Humanities}, publisher = {NLP Association of India (NLPAI)}, pages = {55--63}, url = {https://aclanthology.org/2021.nlp4dh-1.7}, urldate = {2023-11-02} } @software{arnold2022, title = {Quid v.2.2.1}, author = {Frederik Arnold}, year = 2022, publisher = {Zenodo}, doi = {10.5281/zenodo.7106761}, version = {2.2.1} } @inproceedings{arnold2022b, title = {{Lesen, was wirklich wichtig ist - Die Identifikation von Schlüsselstellen durch ein neues Instrument zur Zitatanalyse}}, author = {Arnold, Frederik and Fiechter, Benjamin}, year = 2022, booktitle = {{DHd} 2022 Kulturen des digitalen Gedächtnisses. 8. Tagung des Verbands Digital Humanities im deutschsprachigen Raum}, publisher = {DHd-Verband}, doi = {10.5281/zenodo.6327917} } @inproceedings{arnold2022c, title = {{A} {G}ame with {C}omplex {R}ules: {L}iterature {R}eferences in {L}iterary {S}tudies}, author = {Arnold, Frederik and J{\"a}schke, Robert}, year = 2022, booktitle = {Proceedings of the Workshop on {U}nderstanding {LI}terature references in academic full {TE}xt}, publisher = {CEUR Workshop Proceedings}, pages = {7--15}, url = {https://ceur-ws.org/Vol-3220/paper1.pdf}, urldate = {2023-11-02} } @inproceedings{devlin2019, title = {{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, year = 2019, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, publisher = {Association for Computational Linguistics}, pages = {4171--4186}, doi = {10.18653/v1/N19-1423} } @article{hochreiter1997, title = {{Long Short-Term Memory}}, author = {Hochreiter, Sepp and Schmidhuber, Jürgen}, year = 1997, journal = {Neural Computation}, number = 9, pages = {1735--1780}, doi = {10.1162/neco.1997.9.8.1735}, issue = 8 } @inproceedings{bromley1993, title = {Signature Verification Using a Siamese Time Delay Neural Network}, author = {Jane Bromley and Isabelle Guyon and Yann LeCun and Eduard S{\"{a}}ckinger and Roopak Shah}, year = 1993, booktitle = {Advances in Neural Information Processing Systems}, volume = 6, url = {https://dl.acm.org/doi/10.5555/2987189.2987282} } @inproceedings{hosseini2019, title = {{EXCITE} – A Toolchain to Extract, Match and Publish Open Literature References}, author = {Hosseini, Azam and Ghavimi, Behnam and Boukhers, Zeyd and Mayr, Philipp}, year = 2019, booktitle = {2019 {ACM/IEEE} Joint Conference on Digital Libraries ({JCDL})}, pages = {432--433}, doi = {10.1109/JCDL.2019.00105} } @inproceedings{koerner2017, title = {Evaluating Reference String Extraction Using Line-Based Conditional Random Fields: A Case Study with German Language Publications}, author = {K{\"o}rner, Martin and Ghavimi, Behnam and Mayr, Philipp and Hartmann, Heinrich and Staab, Steffen}, year = 2017, booktitle = {New Trends in Databases and Information Systems}, publisher = {Springer International Publishing}, pages = {137--145}, editor = {Kirikova, M{\={a}}r{\={\i}}te and N{\o}rv{\aa}g, Kjetil and Papadopoulos, George A. and Gamper, Johann and Wrembel, Robert and Darmont, J{\'e}r{\^o}me and Rizzi, Stefano} } @inproceedings{boukhers2019, title = {An End-to-End Approach for Extracting and Segmenting High-Variance References from PDF Documents}, author = {Boukhers, Zeyd and Ambhore, Shriharsh and Staab, Steffen}, year = 2019, booktitle = {2019 {ACM/IEEE} Joint Conference on Digital Libraries ({JCDL})}, pages = {186--195}, doi = {10.1109/JCDL.2019.00035} } @misc{grobid, title = {GROBID}, year = {2008--2022}, publisher = {GitHub}, howpublished = {\url{https://github.com/kermitt2/grobid}}, archiveprefix = {swh}, eprint = {1:dir:dab86b296e3c3216e2241968f0d63b68e8209d3c} } @article{tkaczyk2015, title = {{CERMINE}: automatic extraction of structured metadata from scientific literature}, author = {Tkaczyk, Dominika and Szostek, Paweł and Fedoryszak, Mateusz and Dendek, Piotr Jan and Bolikowski, {\L}ukasz}, year = 2015, journal = {International Journal on Document Analysis and Recognition (IJDAR)}, publisher = {Springer Berlin Heidelberg}, number = 18, pages = {317--335}, doi = {10.1007/s10032-015-0249-8}, issue = 4 } @article{prasad2018, title = {Neural {ParsCit}: a deep learning-based reference string parser}, author = {Prasad, Animesh and Kaur, Manpreet and Kan, Min-Yen}, year = 2018, journal = {International Journal on Digital Libraries}, number = 19, pages = {323--337}, doi = {10.1007/s00799-018-0242-1}, issue = 4 } @inproceedings{ramesh2020, title = {{S}ci{WING}{--} A Software Toolkit for Scientific Document Processing}, author = {Ramesh Kashyap, Abhinav and Kan, Min-Yen}, year = 2020, booktitle = {Proceedings of the First Workshop on Scholarly Document Processing}, publisher = {Association for Computational Linguistics}, pages = {113--120}, doi = {10.18653/v1/2020.sdp-1.13} } @inproceedings{grennan2019, title = {GIANT: The 1-Billion Annotated Synthetic Bibliographic-Reference-String Dataset for Deep Citation Parsing}, author = {Grennan, Mark and Schibel, Martin and Collins, Andrew and Beel, Joeran}, year = 2019, booktitle = {27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science}, pages = {101--112} } @inproceedings{thai2020, title = {Using BibTeX to Automatically Generate Labeled Data for Citation Field Extraction}, author = {Dung Thai and Zhiyang Xu and Nicholas Monath and Boris Veytsman and Andrew McCallum}, year = 2020, booktitle = {Automated Knowledge Base Construction}, doi = {10.24432/C5F592} } @misc{colavizza2017, title = {{Annotated References in the Historiography on Venice: 19th–21st centuries}}, author = {Giovanni Colavizza and Matteo Romanello}, year = 2017, journal = {{Journal of Open Humanities Data}}, volume = 3, pages = 2, doi = {10.5334/johd.9} } @incollection{jannidis2019, title = {Was verändert sich eigentlich? {K}orpusanalytisch basierte {W}issenschaftsgeschichte der germanistischen Praxis am Beispiel der Deutschen Vierteljahrsschrift für Literaturwissenschaft und Geistesgeschichte}, author = {Jannidis, Fotis and Martus, Steffen and Konle, Leonhard and Kreutel, Jörn}, year = 2019, booktitle = {Digitale Literaturwissenschaft}, note = {in print} } @inproceedings{doerfel2012, title = {Publication Analysis of the Formal Concept Analysis Community}, author = {Doerfel, Stephan and Jäschke, Robert and Stumme, Gerd}, year = 2012, booktitle = {Formal Concept Analysis}, publisher = {Springer}, series = {Lecture Notes in Artificial Intelligence}, volume = 7278, pages = {77--95}, doi = {10.1007/978-3-642-29892-9_12}, editor = {Domenach, F. and Ignatov, D.I. and Poelmans, J.} } @inproceedings{anzaroot2013, title = {A New Dataset for Fine-Grained Citation Field Extraction}, author = {Sam Anzaroot and Andrew McCallum}, year = 2013, booktitle = {{ICML} Workshop on Peer Reviewing and Publishing Models ({PEER})} } @inproceedings{peters2018, title = {Deep Contextualized Word Representations}, author = {Peters, Matthew E. and Neumann, Mark and Iyyer, Mohit and Gardner, Matt and Clark, Christopher and Lee, Kenton and Zettlemoyer, Luke}, year = 2018, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, publisher = {Association for Computational Linguistics}, pages = {2227--2237}, doi = {10.18653/v1/N18-1202} } @article{tkaczyk2014, title = {{GROTOAP2} - The Methodology of Creating a Large Ground Truth Dataset of Scientific Articles}, author = {Dominika Tkaczyk and Pawel Szostek and Lukasz Bolikowski}, year = 2014, journal = {D Lib Mag.}, number = 20 } @article{cox2005, title = {What Are Communities of Practice? {A} Comparative Review of Four Seminal Works}, author = {Cox, Andrew}, year = 2005, journal = {Journal of Information Science}, number = 31, pages = {527--540} } @mastersthesis{kalaidopoulou2016, title = {similarity texter: {A} text-comparison web tool based on the “simtext” algorithm}, author = {Kalaidopoulou, Sofia}, year = 2016, url = {https://people.f4.htw-berlin.de/~weberwu/simtexter/522789_Sofia-Kalaidopoulou_bachelor-thesis.pdf}, urldate = {2023-11-02}, note = {source code available at \url{https://people.f4.htw-berlin.de/~weberwu/simtexter/app.html}}, type = {Bachelor's thesis}, school = {Hochschule für Technik und Wirtschaft} } @webpage{buechler2016, title = {{TRACER}: A Text Reuse Detection Machine}, author = {Büchler, Marco}, year = 2016, doi = {21.11101/0000-0007-C9CA-3} } @webpage{franzini2016, title = {{TRACER} Text Reuse Detection Machine: The user manual}, author = {Franzini, G., Franzini E., Bulert, K., Büchler M., Moritz, M.}, year = 2016, url = {https://tracer.gitbook.io/manual/}, lastchecked = {2023-11-02} } @webpage{reeve2020, title = {JonathanReeve/text-matcher: First Zenodo release}, author = {Jonathan Reeve}, year = 2020, doi = {10.5281/zenodo.3937738}, note = {version 0.1.6}, howpublished = {Zenodo} } @article{altschul1990, title = {Basic local alignment search tool}, author = {Altschul, Stephen F. and Gish, Warren and Miller, Webb and Myers, Eugene W. and Lipman, David J.}, year = 1990, journal = {Journal of Molecular Biology}, number = 215, pages = {403--410}, doi = {10.1016/S0022-2836(05)80360-2}, issue = 3 } @inproceedings{smith2014, title = {Detecting and Modeling Local Text Reuse}, author = {Smith, David A. and Cordell, Ryan and Dillon, Elizabeth Maddock and Stramp, Nick and Wilkerson, John}, year = 2014, booktitle = {Proceedings of the 14th ACM/IEEE-CS Joint Conference on Digital Libraries}, location = {London, United Kingdom}, publisher = {IEEE Press}, series = {JCDL '14}, pages = {183–192}, numpages = 10 } @webpage{teiWebsite, title = {{TEI P5}: Guidelines for Electronic Text Encoding and Interchange, Version 4.4.0}, author = {{TEI Consortium, eds.}}, year = 2022, url = {https://www.tei-c.org/Guidelines/P5/}, urldate = {2022-04-29} } @webpage{argulitWebsite, title = {The making of plausibility in interpretive texts. {Analyses} of argumentative practices in literary studies}, author = {Simone Winko}, year = {2017--2020}, url = {https://gepris.dfg.de/gepris/projekt/372804438?language=en}, urldate = {2023-11-02}, note = {DFG-funded research project (grant no. 372804438)} } @book{judenbuche, title = {Die Judenbuche}, author = {Droste-Hülshoff, Annette von}, year = 1979, publisher = {Insel Verlag}, url = {https://www.projekt-gutenberg.org/droste/judenbch/index.html}, urldate = {2023-11-02} } @incollection{kohlhaas, title = {Michael {Kohlhaas}}, author = {Kleist, Heinrich von}, year = 1978, booktitle = {Werke und Briefe in vier Bänden}, publisher = {CreateSpace Independent Publishing Platform}, pages = {7--113}, url = {http://www.zeno.org/nid/2000516902X}, urldate = {2023-11-02}, editor = {Holzinger, Michael} } @incollection{klauser1996, title = {Die {Judenbuche} (1841)}, author = {Klauser, Olivia}, year = 1996, booktitle = {Erzählkunst der Vormoderne}, publisher = {Peter Lang}, pages = {181--197}, editor = {Tarot, Ralf} } @webpage{shakespeareWebsite, title = {{T}o {Q}uote or {N}ot to {Q}uote}, author = {Miller, Derek}, url = {http://shakespeare.visualizingbroadway.com/index.html}, urldate = {2023-11-02} } @article{levenshtein1966, title = {Binary Codes Capable of Correcting Deletions, Insertions and Reversals}, author = {Levenshtein, Vladimir I.}, year = 1966, journal = {Soviet Physics Doklady}, number = 10, pages = {707--710}, issue = 8 } @software{lshPython, title = {{ekzhu/datasketch: Improved performance for MinHash and MinHashLSH}}, author = {Eric Zhu and Vadim Markovtsev and aastafiev and Wojciech Łukasiewicz and ae-foster and Jordan Martin and Ekevoo and Kevin Mann and Keyur Joshi and Spandan Thakur and Stefano Ortolani and Titusz and Vojtech Letal and Zac Bentley and fpug}, year = 2020, publisher = {Zenodo}, doi = {10.5281/zenodo.4323502}, version = {1.5.2} } @article{slaney2008, title = {Locality-Sensitive Hashing for Finding Nearest Neighbors}, author = {Slaney, Malcolm and Casey, Michael}, year = 2008, journal = {IEEE Signal Processing Magazine}, number = 25, pages = {128--131}, doi = {10.1109/MSP.2007.914237}, issue = 2 } @inproceedings{paice1980, title = {The Automatic Generation of Literature Abstracts: An Approach Based on the Identification of Self-Indicating Phrases}, author = {Paice, C. D.}, year = 1980, booktitle = {Proceedings of the 3rd Annual ACM Conference on Research and Development in Information Retrieval}, location = {Cambridge, England}, publisher = {Butterworth \& Co.}, series = {SIGIR '80}, pages = {172–191}, numpages = 20 } @incollection{nenkova2012, title = {A Survey of Text Summarization Techniques}, author = {Nenkova, Ani and McKeown, Kathleen}, year = 2012, booktitle = {Mining Text Data}, publisher = {Springer US}, pages = {43--76}, doi = {10.1007/978-1-4614-3223-4_3}, editor = {Aggarwal, Charu C. and Zhai, ChengXiang} } @book{scott2006, title = {Textual Patterns: Key Words and Corpus Analysis in Language Education}, author = {Scott, M. and Tribble, C.}, year = 2006, publisher = {J. Benjamins}, series = {Studies in corpus linguistics}, lccn = 2006040658 } @article{hoad2003, title = {Methods for Identifying Versioned and Plagiarized Documents}, author = {Hoad, Timothy C. and Zobel, Justin}, year = 2003, journal = {J. Am. Soc. Inf. Sci. Technol.}, publisher = {John Wiley & Sons, Inc.}, number = 54, pages = {203–215}, doi = {10.1002/asi.10170}, issue_date = {February 1, 2003}, issue = 3, numpages = 13 } @article{yao2017, title = {Recent advances in document summarization}, author = {Yao, Jin-ge and Wan, Xiaojun and Xiao, Jianguo}, year = 2017, journal = {Knowledge and Information Systems}, publisher = {Springer}, number = 53, pages = {297--336}, doi = {10.1007/s10115-017-1042-4}, issue = 2 } @webpage{copyFindWebsite, title = {Copyfind}, author = {Bloomfield, Lou}, year = 2016, url = {https://plagiarism.bloomfieldmedia.com/software/copyfind/}, urldate = {2023-11-02} }