@inproceedings{rodriguez2023,
	address = {Remote},
	title = {Speech-to-text recognition for multilingual spoken data in language documentation},
	url = {https://aclanthology.org/2023.computel-1.17},
	urldate = {2024-03-04},
	booktitle = {Proceedings of the {Sixth} {Workshop} on the {Use} of {Computational} {Methods} in the {Study} of {Endangered} {Languages}},
	publisher = {Association for Computational Linguistics},
	author = {Rodríguez, Lorena Martín and Cox, Christopher},
	editor = {Harrigan, Atticus and Chaudhary, Aditi and Rijhwani, Shruti and Moeller, Sarah and Arppe, Antti and Palmer, Alexis and Henke, Ryan and Rosenblum, Daisy},
	month = mar,
	year = {2023},
	pages = {117--123},
}

@book{maci_corpus_2022,
	title = {Corpus {Linguistics} and {Translation} {Tools} for {Digital} {Humanities}: {Research} {Methods} and {Applications}},
	isbn = {978-1-350-27523-2},
	shorttitle = {Corpus {Linguistics} and {Translation} {Tools} for {Digital} {Humanities}},
	abstract = {Presenting the digital humanities as both a domain of practice and as a set of methodological approaches to be applied to corpus linguistics and translation, chapters in this volume provide a novel and original framework to triangulate research for pursuing both scientific and educational goals within the digital humanities. They also highlight more broadly the importance of data triangulation in corpus linguistics and translation studies.Putting forward practical applications for digging into data, this book is a detailed examination of how to integrate quantitative and qualitative approaches through case studies, sample analysis and practical examples.},
	language = {en},
	publisher = {Bloomsbury Publishing},
	author = {Maci, Stefania M. and Sala, Michele},
	month = jul,
	year = {2022},
	note = {Google-Books-ID: oJRoEAAAQBAJ},
	keywords = {Computers / Artificial Intelligence / Natural Language Processing, Language Arts \& Disciplines / Linguistics / General, Language Arts \& Disciplines / Linguistics / Pragmatics, Language Arts \& Disciplines / Linguistics / Semantics, Reference / Research},
}

Presenting the digital humanities as both a domain of practice and as a set of methodological approaches to be applied to corpus linguistics and translation, chapters in this volume provide a novel and original framework to triangulate research for pursuing both scientific and educational goals within the digital humanities. They also highlight more broadly the importance of data triangulation in corpus linguistics and translation studies.Putting forward practical applications for digging into data, this book is a detailed examination of how to integrate quantitative and qualitative approaches through case studies, sample analysis and practical examples.

@book{adolphs_routledge_2020,
	address = {London},
	title = {The {Routledge} {Handbook} of {English} {Language} and {Digital} {Humanities}},
	isbn = {978-1-00-303175-8},
	abstract = {The Routledge Handbook of English Language and Digital Humanities serves as a reference point for key developments related to the ways in which the digital turn has shaped the study of the English language and of how the resulting methodological approaches have permeated other disciplines. It draws on modern linguistics and discourse analysis for its analytical methods and applies these approaches to the exploration and theorisation of issues within the humanities.

Divided into three sections, this handbook covers: 



sources and corpora; 


analytical approaches; 


English language at the interface with other areas of research in the digital humanities.


In covering these areas, more traditional approaches and methodologies in the humanities are recast and research challenges are re-framed through the lens of the digital. The essays in this volume highlight the opportunities for new questions to be asked and long-standing questions to be reconsidered when drawing on the digital in humanities research.

This is a ground-breaking collection of essays offering incisive and essential reading for anyone with an interest in the English language and digital humanities.},
	publisher = {Routledge},
	editor = {Adolphs, Svenja and Knight, Dawn},
	month = may,
	year = {2020},
	doi = {10.4324/9781003031758},
}

The Routledge Handbook of English Language and Digital Humanities serves as a reference point for key developments related to the ways in which the digital turn has shaped the study of the English language and of how the resulting methodological approaches have permeated other disciplines. It draws on modern linguistics and discourse analysis for its analytical methods and applies these approaches to the exploration and theorisation of issues within the humanities. Divided into three sections, this handbook covers: sources and corpora; analytical approaches; English language at the interface with other areas of research in the digital humanities. In covering these areas, more traditional approaches and methodologies in the humanities are recast and research challenges are re-framed through the lens of the digital. The essays in this volume highlight the opportunities for new questions to be asked and long-standing questions to be reconsidered when drawing on the digital in humanities research. This is a ground-breaking collection of essays offering incisive and essential reading for anyone with an interest in the English language and digital humanities.

@book{bubenhofer_visuelle_2020,
	address = {Boston},
	edition = {1st ed},
	series = {Linguistik - impulse \& tendenzen},
	title = {Visuelle {Linguistik}: zur {Genese}, {Funktion} und {Kategorisierung} von {Diagrammen} in der {Sprachwissenschaft}},
	isbn = {978-3-11-069869-5},
	shorttitle = {Visuelle linguistik},
	number = {90},
	publisher = {De Gruyter},
	author = {Bubenhofer, Noah},
	year = {2020},
}

@article{onanuga_transnationalizing_2020,
	title = {Transnationalizing humour on social media: {A} linguistic analysis of ideology, identity and didactics in {Robert} {Mugabe} {Quotes} memes1},
	volume = {35},
	issn = {2055-7671},
	shorttitle = {Transnationalizing humour on social media},
	url = {https://doi.org/10.1093/llc/fqz019},
	doi = {10.1093/llc/fqz019},
	abstract = {Humour relies on dominant cultural values and outlooks in its environment in enacting its comic content. However, since humour sometimes encompasses global experiences, it often transcends artificial human barriers. Its transcendence has been facilitated through online digitized content, in the present case—Internet memes. In exploring transnationalization, fifty purposively selected memes are culled from the Facebook group Robert Mugabe Quotes and subjected to critical linguistic analysis. In the evaluation of the data which is achieved through the linguistic examination of cross-cultural themes in the formulation of identity, didactics, and ideology, sixteen memes, representative of the overarching tripartite concerns, are used as exemplifications. Reliant on the bipartite postulations of Critical Linguistic Stylistics—a linguistic theory that examines the style and peculiarities of linguistic data—and Relief Theory of Humour—which considers humour as a platform for the assuagement of tension and emotions, the memes are testamental of prevailing concerns— politics, technology, social/international relations, sex, male–female relations, etc.—in the human society at large. Linguistic markers such as oppositional expressions, capitalization, and other graphological features are annexed in meaning-formation. I conclude that although humour is generally regarded as a light-hearted routine geared towards the provision of momentary relief, a close scrutiny reveals that deep messages targeted at stimulating consciousness and social transformation find provenance in these artefacts.},
	number = {2},
	urldate = {2021-03-04},
	journal = {Digital Scholarship in the Humanities},
	author = {Onanuga, Paul},
	month = jun,
	year = {2020},
	pages = {399--416},
}

Humour relies on dominant cultural values and outlooks in its environment in enacting its comic content. However, since humour sometimes encompasses global experiences, it often transcends artificial human barriers. Its transcendence has been facilitated through online digitized content, in the present case—Internet memes. In exploring transnationalization, fifty purposively selected memes are culled from the Facebook group Robert Mugabe Quotes and subjected to critical linguistic analysis. In the evaluation of the data which is achieved through the linguistic examination of cross-cultural themes in the formulation of identity, didactics, and ideology, sixteen memes, representative of the overarching tripartite concerns, are used as exemplifications. Reliant on the bipartite postulations of Critical Linguistic Stylistics—a linguistic theory that examines the style and peculiarities of linguistic data—and Relief Theory of Humour—which considers humour as a platform for the assuagement of tension and emotions, the memes are testamental of prevailing concerns— politics, technology, social/international relations, sex, male–female relations, etc.—in the human society at large. Linguistic markers such as oppositional expressions, capitalization, and other graphological features are annexed in meaning-formation. I conclude that although humour is generally regarded as a light-hearted routine geared towards the provision of momentary relief, a close scrutiny reveals that deep messages targeted at stimulating consciousness and social transformation find provenance in these artefacts.

@article{arnold2019b,
	title = {Beyond lexical frequencies: using {R} for text analysis in the digital humanities},
	volume = {53},
	issn = {1574-020X, 1574-0218},
	shorttitle = {Beyond lexical frequencies},
	url = {http://link.springer.com/10.1007/s10579-019-09456-6},
	doi = {10.1007/s10579-019-09456-6},
	abstract = {This paper presents a combination of R packages—user contributed toolkits written in a common core programming language—to facilitate the humanistic investigation of digitised, text-based corpora. Our survey of text analysis packages includes those of our own creation (cleanNLP and fasttextM) as well as packages built by other research groups (stringi, readtext, hyphenatr, quanteda, and hunspell). By operating on generic object types, these packages unite research innovations in corpus linguistics, natural language processing, machine learning, statistics, and digital humanities. We begin by extrapolating on the theoretical benefits of R as an elaborate gluing language for bringing together several areas of expertise and compare it to linguistic concordancers and other tool-based approaches to text analysis in the digital humanities. We then showcase the practical benefits of an ecosystem by illustrating how R packages have been integrated into a digital humanities project. Throughout, the focus is on moving beyond the bag-ofwords, lexical frequency model by incorporating linguistically-driven analyses in research.},
	language = {en},
	number = {4},
	urldate = {2024-03-05},
	journal = {Language Resources and Evaluation},
	author = {Arnold, Taylor and Ballier, Nicolas and Lissón, Paula and Tilton, Lauren},
	month = dec,
	year = {2019},
	pages = {707--733},
}

This paper presents a combination of R packages—user contributed toolkits written in a common core programming language—to facilitate the humanistic investigation of digitised, text-based corpora. Our survey of text analysis packages includes those of our own creation (cleanNLP and fasttextM) as well as packages built by other research groups (stringi, readtext, hyphenatr, quanteda, and hunspell). By operating on generic object types, these packages unite research innovations in corpus linguistics, natural language processing, machine learning, statistics, and digital humanities. We begin by extrapolating on the theoretical benefits of R as an elaborate gluing language for bringing together several areas of expertise and compare it to linguistic concordancers and other tool-based approaches to text analysis in the digital humanities. We then showcase the practical benefits of an ecosystem by illustrating how R packages have been integrated into a digital humanities project. Throughout, the focus is on moving beyond the bag-ofwords, lexical frequency model by incorporating linguistically-driven analyses in research.

@article{hinrichs_language_2019,
	title = {Language technology for digital humanities: introduction to the special issue},
	volume = {53},
	issn = {1574-020X, 1574-0218},
	shorttitle = {Language technology for digital humanities},
	url = {http://link.springer.com/10.1007/s10579-019-09482-4},
	doi = {10.1007/s10579-019-09482-4},
	language = {en},
	number = {4},
	urldate = {2021-06-08},
	journal = {Language Resources and Evaluation},
	author = {Hinrichs, Erhard and Hinrichs, Marie and Kübler, Sandra and Trippel, Thorsten},
	month = dec,
	year = {2019},
	pages = {559--563},
}

@article{schwandt_digitale_2018,
	title = {Digitale {Methoden} für die {Historische} {Semantik}. {Auf} den {Spuren} von {Begriffen} in digitalen {Korpora}},
	volume = {44},
	issn = {0340-613X},
	url = {https://pub.uni-bielefeld.de/record/2919326},
	abstract = {One of the biggest challenges associated with semantic analysis is to obtain a distance from existing semantic knowledge. Methods from the field of Digital Humanities allow us to find new ways to cope with that challenge. Text mining or topic modeling tools offer a new perspective on words and their combination within a text. The following article highlights the relevance of digital methods for historical semantics, using the Latin term virtus and its medieval use as an example. It raises the question of genre and diachronic semantic change and demonstrates howdigital tools have the potential to not only challenge our knowledge about texts but also help to reorganize what we already know.},
	language = {ger},
	number = {1},
	urldate = {2021-08-26},
	journal = {GESCHICHTE UND GESELLSCHAFT},
	author = {Schwandt, Silke},
	year = {2018},
}

One of the biggest challenges associated with semantic analysis is to obtain a distance from existing semantic knowledge. Methods from the field of Digital Humanities allow us to find new ways to cope with that challenge. Text mining or topic modeling tools offer a new perspective on words and their combination within a text. The following article highlights the relevance of digital methods for historical semantics, using the Latin term virtus and its medieval use as an example. It raises the question of genre and diachronic semantic change and demonstrates howdigital tools have the potential to not only challenge our knowledge about texts but also help to reorganize what we already know.

@incollection{scheu_qualitative_2018,
	address = {Wiesbaden},
	title = {Qualitative {Textanalyse}. {Blaupause} und {Potenziale} (teil-)automatisierter {Verfahren}},
	isbn = {978-3-658-18404-9 978-3-658-18405-6},
	url = {http://link.springer.com/10.1007/978-3-658-18405-6_20},
	language = {de},
	urldate = {2021-06-08},
	booktitle = {Auswertung qualitativer {Daten}},
	publisher = {Springer Fachmedien Wiesbaden},
	author = {Scheu, Andreas M. and Vogelgesang, Jens and Scharkow, Michael},
	editor = {Scheu, Andreas M.},
	year = {2018},
	doi = {10.1007/978-3-658-18405-6_20},
	pages = {309--322},
}

@book{lobin_digitale_2018,
	address = {Berlin/Boston},
	series = {Germanistische {Sprachwissenschaft} um 2020},
	title = {Digitale {Infrastrukturen} für die germanistische {Forschung}},
	volume = {6},
	isbn = {978-3-11-053866-3},
	abstract = {Die moderne sprachwissenschaftliche Forschung nutzt in zunehmender Weise digitale Forschungsinfrastrukturen und Informationssysteme. Diese Entwicklung begann um die Jahrtausendwende und beschleunigt sich seither. Der Band thematisiert nationale und europäische Infrastrukturverbünde und verschiedene Sprachressourcen aus der germanistischen Sprachwissenschaft, die über digitale Infrastrukturen auffindbar, zugreifbar und (wieder-)verwendbar sind.},
	publisher = {De Gruyter},
	editor = {Lobin, Henning and Schneider, Roman and Witt, Andreas},
	year = {2018},
}

Die moderne sprachwissenschaftliche Forschung nutzt in zunehmender Weise digitale Forschungsinfrastrukturen und Informationssysteme. Diese Entwicklung begann um die Jahrtausendwende und beschleunigt sich seither. Der Band thematisiert nationale und europäische Infrastrukturverbünde und verschiedene Sprachressourcen aus der germanistischen Sprachwissenschaft, die über digitale Infrastrukturen auffindbar, zugreifbar und (wieder-)verwendbar sind.

@article{haosun2017a,
	title = {Verifying the {Authorship} of the {Yasunari} {Kawabata} {Novel} {The} {Sound} of the {Mountain}},
	volume = {7},
	issn = {21595291, 21595305},
	url = {http://www.davidpublisher.org/index.php/Home/Article/index?id=32314.html},
	doi = {10.17265/2159-5291/2017.05.001},
	abstract = {Yasunari Kawabata was a famous Japanese novelist and the winner of the 1968 Nobel Prize in Literature. However, considerable debate persists concerning the authorship of his novel, The Sound of the Mountain, which some claim was in fact written by another celebrated author, Yukio Mishima. In this research, we attempt to resolve this issue by applying character bigrams, part-of-speech bigrams, and phrase pattern analysis stylometric features, and principal component analysis, hierarchical cluster analysis, and random forests as authorship attribution methods. As a result, we obtained compelling evidence to show that Yukio Mishima was not the author of The Sound of the Mountain.},
	language = {en},
	number = {5},
	urldate = {2024-03-04},
	journal = {Journal of Mathematics and System Science},
	author = {{Hao Sun} and {Mingzhe Jin}},
	month = may,
	year = {2017},
}

Yasunari Kawabata was a famous Japanese novelist and the winner of the 1968 Nobel Prize in Literature. However, considerable debate persists concerning the authorship of his novel, The Sound of the Mountain, which some claim was in fact written by another celebrated author, Yukio Mishima. In this research, we attempt to resolve this issue by applying character bigrams, part-of-speech bigrams, and phrase pattern analysis stylometric features, and principal component analysis, hierarchical cluster analysis, and random forests as authorship attribution methods. As a result, we obtained compelling evidence to show that Yukio Mishima was not the author of The Sound of the Mountain.

@article{mambrini_treebanking_2016,
	title = {Treebanking in the world of {Thucydides}. {Linguistic} annotation for the {Hellespont} {Project}},
	volume = {010},
	issn = {1938-4122},
	number = {2},
	journal = {Digital Humanities Quarterly},
	author = {Mambrini, Francesco},
	month = jun,
	year = {2016},
}

@article{armitage_longing_2016,
	title = {Longing for the {Longue} {Durée}},
	volume = {107},
	number = {2},
	journal = {Isis},
	author = {Armitage, David and Guldi, Jo},
	year = {2016},
	pages = {353--357},
}

@article{jensen_linguistics_2014,
	title = {Linguistics in the digital humanities: (computational) corpus linguistics},
	volume = {30},
	issn = {1901-9726, 0900-9671},
	shorttitle = {Linguistics in the digital humanities},
	url = {https://tidsskrift.dk/mediekultur/article/view/15968},
	doi = {10.7146/mediekultur.v30i57.15968},
	abstract = {Corpus linguistics has been closely intertwined with digital technology since the introduction of university computer mainframes in the 1960s. Making use of both digitized data in the form of the language corpus and computational methods of analysis involving concordancers and statistics software, corpus linguistics arguably has a place in the digital humanities. Still, it remains obscure and fi gures only sporadically in the literature on the digital humanities. Th is article provides an overview of the main principles of corpus linguistics and the role of computer technology in relation to data and method and also off ers a bird's-eye view of the history of corpus linguistics with a focus on its intimate relationship with digital technology and how digital technology has impacted the very core of corpus linguistics and shaped the identity of the corpus linguist. Ultimately, the article is oriented towards an acknowledgment of corpus linguistics' alignment with the digital humanities.},
	number = {57},
	urldate = {2023-02-24},
	journal = {MedieKultur: Journal of media and communication research},
	author = {Jensen, Kim Ebensgaard},
	month = dec,
	year = {2014},
	keywords = {automatic annotation, computational tools in linguistic analysis, concordancer, corpus linguistics, data in the humanities, digitization, method},
}

Corpus linguistics has been closely intertwined with digital technology since the introduction of university computer mainframes in the 1960s. Making use of both digitized data in the form of the language corpus and computational methods of analysis involving concordancers and statistics software, corpus linguistics arguably has a place in the digital humanities. Still, it remains obscure and fi gures only sporadically in the literature on the digital humanities. Th is article provides an overview of the main principles of corpus linguistics and the role of computer technology in relation to data and method and also off ers a bird's-eye view of the history of corpus linguistics with a focus on its intimate relationship with digital technology and how digital technology has impacted the very core of corpus linguistics and shaped the identity of the corpus linguist. Ultimately, the article is oriented towards an acknowledgment of corpus linguistics' alignment with the digital humanities.

@article{kretzschmar_computer_2014,
	title = {Computer {Simulation} of {Dialect} {Feature} {Diffusion}},
	volume = {2},
	issn = {2049-7547},
	doi = {10.1017/jlg.2014.2},
	number = {1},
	journal = {Journal of Linguistic Geography},
	author = {Kretzschmar, William A. and Juuso, Ilkka and Bailey, C. Thomas},
	month = mar,
	year = {2014},
	pages = {41--57},
}

@article{piotrowski_natural_2012,
	title = {Natural {Language} {Processing} for {Historical} {Texts}},
	volume = {5},
	issn = {1947-4040, 1947-4059},
	url = {http://www.morganclaypool.com/doi/abs/10.2200/S00436ED1V01Y201207HLT017},
	doi = {10.2200/S00436ED1V01Y201207HLT017},
	abstract = {More and more historical texts are becoming available in digital form. Digitization of paper documents is motivated by the aim of preserving cultural heritage and making it more accessible, both to laypeople and scholars. As digital images cannot be searched for text, digitization projects increasingly strive to create digital text, which can be searched and otherwise automatically processed, in addition to facsimiles. Indeed, the emerging field of digital humanities heavily relies on the availability of digital text for its studies.

Together with the increasing availability of historical texts in digital form, there is a growing interest in applying natural language processing (NLP) methods and tools to historical texts. However, the specific linguistic properties of historical texts -- the lack of standardized orthography, in particular -- pose special challenges for NLP.

This book aims to give an introduction to NLP for historical texts and an overview of the state of the art in this field. The book starts with an overview of methods for the acquisition of historical texts (scanning and OCR), discusses text encoding and annotation schemes, and presents examples of corpora of historical texts in a variety of languages. The book then discusses specific methods, such as creating part-of-speech taggers for historical languages or handling spelling variation. A final chapter analyzes the relationship between NLP and the digital humanities.

Certain recently emerging textual genres, such as SMS, social media, and chat messages, or newsgroup and forum postings share a number of properties with historical texts, for example, nonstandard orthography and grammar, and profuse use of abbreviations. The methods and techniques required for the effective processing of historical texts are thus also of interest for research in other domains.},
	language = {en},
	number = {2},
	urldate = {2013-01-19},
	journal = {Synthesis Lectures on Human Language Technologies},
	author = {Piotrowski, Michael},
	month = sep,
	year = {2012},
	keywords = {goal\_Capture, goal\_Enrichment, meta\_GiveOverview},
	pages = {1--157},
}

More and more historical texts are becoming available in digital form. Digitization of paper documents is motivated by the aim of preserving cultural heritage and making it more accessible, both to laypeople and scholars. As digital images cannot be searched for text, digitization projects increasingly strive to create digital text, which can be searched and otherwise automatically processed, in addition to facsimiles. Indeed, the emerging field of digital humanities heavily relies on the availability of digital text for its studies. Together with the increasing availability of historical texts in digital form, there is a growing interest in applying natural language processing (NLP) methods and tools to historical texts. However, the specific linguistic properties of historical texts – the lack of standardized orthography, in particular – pose special challenges for NLP. This book aims to give an introduction to NLP for historical texts and an overview of the state of the art in this field. The book starts with an overview of methods for the acquisition of historical texts (scanning and OCR), discusses text encoding and annotation schemes, and presents examples of corpora of historical texts in a variety of languages. The book then discusses specific methods, such as creating part-of-speech taggers for historical languages or handling spelling variation. A final chapter analyzes the relationship between NLP and the digital humanities. Certain recently emerging textual genres, such as SMS, social media, and chat messages, or newsgroup and forum postings share a number of properties with historical texts, for example, nonstandard orthography and grammar, and profuse use of abbreviations. The methods and techniques required for the effective processing of historical texts are thus also of interest for research in other domains.

@incollection{geyken_compiling_2012,
	title = {Compiling large historical reference corpora of {German}: {Quality} {Assurance}, {Interoperability} and {Collaboration} in the {Process} of {Publication} of {Digitized} {Historical} {Prints}},
	shorttitle = {Compiling large historical reference corpora of {German}},
	booktitle = {Digital humanities 2012},
	author = {Geyken, Alexander and Gloning, Thomas and Stäcker, Thomas},
	year = {2012},
	pages = {54--56},
}

@inproceedings{ritter2011,
	address = {Edinburgh, Scotland, UK.},
	title = {Named {Entity} {Recognition} in {Tweets}: {An} {Experimental} {Study}},
	shorttitle = {Named {Entity} {Recognition} in {Tweets}},
	url = {https://aclanthology.org/D11-1141},
	urldate = {2024-03-04},
	booktitle = {Proceedings of the 2011 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
	publisher = {Association for Computational Linguistics},
	author = {Ritter, Alan and Clark, Sam and {Mausam} and Etzioni, Oren},
	editor = {Barzilay, Regina and Johnson, Mark},
	month = jul,
	year = {2011},
	pages = {1524--1534},
}

@article{mehler_ehumanities_2011,
	title = {Der {eHumanities} {Desktop} als {Werkzeug} in der historischen {Semantik}: {Funktionsspektren} und {Einsatzszenarien}},
	volume = {26},
	issn = {2190-6858},
	shorttitle = {Der {eHumanities} {Desktop} als {Werkzeug} in der historischen {Semantik}},
	url = {https://pub.uni-bielefeld.de/record/2902769},
	language = {ger},
	number = {1},
	urldate = {2021-08-26},
	journal = {Journal for Language Technology and Computational Linguistics (JCLC)},
	author = {Mehler, Alexander and Schwandt, Silke and Gleim, Rüdiger and Jussen, Bernhard},
	year = {2011},
}

@incollection{baker_corpus_2010,
	address = {London},
	title = {Corpus {Methods} in {Linguistics}},
	abstract = {This chapter examines how corpus linguistics techniques can be used to aid a range of linguistic analyses.},
	language = {English},
	booktitle = {Research {Methods} in {Linguistics}},
	publisher = {Bloomsbury},
	author = {Baker, Paul},
	year = {2010},
}

This chapter examines how corpus linguistics techniques can be used to aid a range of linguistic analyses.

@article{bamman_computational_2009,
	title = {Computational {Linguistics} and {Classical} {Lexicography}},
	volume = {003},
	issn = {1938-4122},
	number = {1},
	journal = {Digital Humanities Quarterly},
	author = {Bamman, David and Crane, Gregory},
	month = feb,
	year = {2009},
}

@article{hoover_end_2007,
	title = {The {End} of the {Irrelevant} {Text}: {Electronic} {Texts}, {Linguistics}, and {Literary} {Theory}},
	volume = {001},
	issn = {1938-4122},
	shorttitle = {The {End} of the {Irrelevant} {Text}},
	number = {2},
	journal = {Digital Humanities Quarterly},
	author = {Hoover, David},
	month = sep,
	year = {2007},
}

@incollection{jannidis_computerphilologie_2007,
	address = {Stuttgart},
	title = {Computerphilologie},
	volume = {2 (Methoden und Theorien)},
	language = {de},
	booktitle = {Handbuch {Literaturwissenschaft}},
	publisher = {Metzler},
	author = {Jannidis, Fotis},
	editor = {Anz, Thomas},
	year = {2007},
	keywords = {*****, AnalyzeStatistically, X-CHECK, act\_Publishing, goal\_Enrichment, meta\_GiveOverview, obj\_DigitalHumanities, obj\_Tools, t\_Encoding, x\_astree},
	pages = {27--40},
}

@article{leenders_welke_2005,
	title = {Welke eisen stelt de historische geografie aan de digitalisering van toponiemen?},
	volume = {36},
	journal = {Naamkunde},
	author = {Leenders, Karel A. H. W.},
	year = {2005},
	pages = {103--119},
}

@book{meister_computing_2003,
	address = {Berlin},
	title = {Computing action. {A} narratological approach},
	isbn = {978-3-11-017628-5},
	publisher = {De Gruyter},
	author = {Meister, Jan Christoph},
	year = {2003},
}

@incollection{herold_computerphilologie_2000,
	address = {Amsterdam},
	series = {Applicatio},
	title = {Computerphilologie als {Methode} der {Historisch}-quellenkundlichen {Analyse} spätmittelalterlicher {Briefe}},
	volume = {15},
	author = {Herold, Jürgen},
	year = {2000},
	keywords = {Brief, Computerphilologie, Historische Fachinformatik, Quellenkritik, historische},
	pages = {129--148},
}

@article{jannidis_was_1999,
	title = {Was ist {Computerphilologie}?},
	url = {http://computerphilologie.digital-humanities.de/jahrbuch/jb1/jannidis-1.html},
	abstract = {Im Zuge seiner weltweiten Verbreitung konnte sich der PC gegen anfängliche Bedenken und Widerstände auch in der Literaturwissenschaft als Werkzeug der täglichen Arbeit etablieren. Anfangs waren es vor allem die Vorteile der Textverarbeitung und deren Entlastung vom mechanischen Aspekt des Schreibens und Wiederschreibens, die den Rechnern den Weg auf die Schreibtische ebneten. Ist aber die Maschine einmal vorhanden, man sich mit geringem Aufwand Zugang zum Internet verschaffen. E-Mail und das World Wide Web eröffnen einfachere Kommunikationswege, dazu kommen die Vorteile des Intranets, also eines universitätseigenen Netzes mit Zugriff auf elektronische Bibliographien und die Bibliothekskataloge einschließlich der Bestellmöglichkeiten vor Ort. Nicht wenige Literaturwissenschaftler haben sich inzwischen auch mit den neueren elektronischen Texten angefreundet, deren einfachen Benutzeroberflächen althergebrachte philologische Tätigkeiten sehr beschleunigen, zum Beispiel die Klärung von Wortbedeutungen mittels der Suche nach Parallelstellen beim selben Autor oder in derselben Epoche.},
	language = {de},
	number = {1},
	journal = {Jahrbuch für Computerphilologie},
	author = {Jannidis, Fotis},
	year = {1999},
	keywords = {*****, goal\_Analysis, goal\_Enrichment, meta\_GiveOverview, obj\_DigitalHumanities},
	pages = {39--60},
}

Im Zuge seiner weltweiten Verbreitung konnte sich der PC gegen anfängliche Bedenken und Widerstände auch in der Literaturwissenschaft als Werkzeug der täglichen Arbeit etablieren. Anfangs waren es vor allem die Vorteile der Textverarbeitung und deren Entlastung vom mechanischen Aspekt des Schreibens und Wiederschreibens, die den Rechnern den Weg auf die Schreibtische ebneten. Ist aber die Maschine einmal vorhanden, man sich mit geringem Aufwand Zugang zum Internet verschaffen. E-Mail und das World Wide Web eröffnen einfachere Kommunikationswege, dazu kommen die Vorteile des Intranets, also eines universitätseigenen Netzes mit Zugriff auf elektronische Bibliographien und die Bibliothekskataloge einschließlich der Bestellmöglichkeiten vor Ort. Nicht wenige Literaturwissenschaftler haben sich inzwischen auch mit den neueren elektronischen Texten angefreundet, deren einfachen Benutzeroberflächen althergebrachte philologische Tätigkeiten sehr beschleunigen, zum Beispiel die Klärung von Wortbedeutungen mittels der Suche nach Parallelstellen beim selben Autor oder in derselben Epoche.

@article{jannidis_computerphilologie_1998,
	title = {Computerphilologie},
	language = {de},
	journal = {Metzler Lexikon Literatur- und Kulturtheorie},
	author = {Jannidis, Fotis},
	year = {1998},
	note = {Jannidis, Fotis: Computerphilologie. In: Ansgar Nünning (Hg.): Metzler Lexikon Literatur- und Kulturtheorie. Stuttgart, Weimar 1998, S. 70-72.},
	keywords = {goal\_Analysis, goal\_Enrichment, meta\_GiveOverview, obj\_DigitalHumanities},
	pages = {70--72},
}

@article{church1993,
	title = {Introduction to the {Special} {Issue} on {Computational} {Linguistics} {Using} {Large} {Corpora}},
	volume = {19},
	url = {https://aclanthology.org/J93-1001},
	number = {1},
	urldate = {2024-03-04},
	journal = {Computational Linguistics},
	author = {Church, Kenneth W. and Mercer, Robert L.},
	editor = {Hirschberg, Julia},
	year = {1993},
	note = {Place: Cambridge, MA
Publisher: MIT Press},
	pages = {1--24},
}

@book{zimmer_elektrifizierung_1991,
	address = {Zürich},
	title = {Die {Elektrifizierung} der {Sprache}. Über {Sprechen}, {Schreiben}, {Computer}, {Gehirne} und {Geist}.},
	isbn = {978-3-251-01099-8},
	language = {Deutsch},
	publisher = {Haffmans},
	author = {Zimmer, Dieter},
	year = {1991},
}

@article{gartner_report_1990,
	title = {Report on {Medieval} {German}},
	number = {5},
	author = {Gärtner, Kurt},
	year = {1990},
	pages = {S. 94--96},
}

@article{frackenpohl_zur_1978,
	title = {Zur {Erstellung} einer computerunterstützten {Grammatik} "{Flexionsmorphologie} des {Frühneuhochdeutschen}"},
	volume = {12},
	issn = {0010-4817},
	url = {https://www.jstor.org/stable/30199933},
	abstract = {[The inflectional morphology of Early New High German is the subject of research at the Forschungsvorhaben Grammatik des Frühneuhochdeutschen at the University of Bonn. Because the High German of the period 1350-1700 shows strong graphemic and morphemic variation, we could not use improved computational lemmatizing alogorithms for computer-assisted analysis. Instead, the data base was extended by philological information manually analyzed. To illustrate our proceeding in setting up the paradigms requires explaining the different algorithms for analyzing verb and noun inflection. The numerous grammatical positions, for most of which little evidence is given, and the prevailing inflected structure precluded an automatic segmentation of verb forms. The program for establishing verb paradigms is based on extended informations (for instance, those about endings, historical inflection classes, preterite suffixes, etc.), and consists of steps for sorting, collecting, and printing. For nouns, the automatic segmentation can be carried out by using as a word-stem the nominative singular form, which always shows a zero-morpheme. In a lemmatizing procedure different from those already in use, the nominative plural form (singular stem + plural formative) is taken as word-stem in order to segmentize the plural cases, and thus avoid the problem of stem variation which is due to the "Pluralumlaut." A noun class is defined by the combination of a singular paradigm, which is characterized by a genitive formative and a plural formative.]},
	number = {1/2},
	urldate = {2019-04-01},
	journal = {Computers and the Humanities},
	author = {Frackenpohl, Gert and Frauenknecht, Harald and Wegera, Klaus-Peter},
	year = {1978},
	pages = {33--42},
}

[The inflectional morphology of Early New High German is the subject of research at the Forschungsvorhaben Grammatik des Frühneuhochdeutschen at the University of Bonn. Because the High German of the period 1350-1700 shows strong graphemic and morphemic variation, we could not use improved computational lemmatizing alogorithms for computer-assisted analysis. Instead, the data base was extended by philological information manually analyzed. To illustrate our proceeding in setting up the paradigms requires explaining the different algorithms for analyzing verb and noun inflection. The numerous grammatical positions, for most of which little evidence is given, and the prevailing inflected structure precluded an automatic segmentation of verb forms. The program for establishing verb paradigms is based on extended informations (for instance, those about endings, historical inflection classes, preterite suffixes, etc.), and consists of steps for sorting, collecting, and printing. For nouns, the automatic segmentation can be carried out by using as a word-stem the nominative singular form, which always shows a zero-morpheme. In a lemmatizing procedure different from those already in use, the nominative plural form (singular stem + plural formative) is taken as word-stem in order to segmentize the plural cases, and thus avoid the problem of stem variation which is due to the "Pluralumlaut." A noun class is defined by the combination of a singular paradigm, which is characterized by a genitive formative and a plural formative.]

@article{nitti_computers_1978,
	title = {Computers and the {Old} {Spanish} {Dictionary}},
	volume = {12},
	issn = {0010-4817},
	url = {https://www.jstor.org/stable/30199934},
	number = {1/2},
	urldate = {2019-04-01},
	journal = {Computers and the Humanities},
	author = {Nitti, John J.},
	year = {1978},
	pages = {43--52},
}

@article{huntsman_computers_1978,
	title = {Computers and {Medieval} {English} {Lexicography}},
	volume = {12},
	issn = {0010-4817},
	url = {https://www.jstor.org/stable/30199935},
	abstract = {[Dictionaries and related language reference works constitute a rich but underexploited resource for the history of languages and of language study in the Middle Ages. Unfortunately, the size and complexity of typical medieval dictionaries make editions and analyses by traditional methods prohibitively expensive in time and money. Using as an example the Latin-Middle English dictionary Medulla grammatice, the paper describes some central problems in the study of medieval English lexicography and the solutions provided by computers, which, with their immense speed, profound memory, and perfect accuracy can help scholars analyze, edit, and promulgate medieval documents and the linguistic data they contain.]},
	number = {1/2},
	urldate = {2019-04-01},
	journal = {Computers and the Humanities},
	author = {Huntsman, Jeffrey F.},
	year = {1978},
	pages = {53--60},
}

[Dictionaries and related language reference works constitute a rich but underexploited resource for the history of languages and of language study in the Middle Ages. Unfortunately, the size and complexity of typical medieval dictionaries make editions and analyses by traditional methods prohibitively expensive in time and money. Using as an example the Latin-Middle English dictionary Medulla grammatice, the paper describes some central problems in the study of medieval English lexicography and the solutions provided by computers, which, with their immense speed, profound memory, and perfect accuracy can help scholars analyze, edit, and promulgate medieval documents and the linguistic data they contain.]

@misc{noauthor_why_nodate,
	title = {Why {Linguists} {Should} {Care} about {Digital} {Humanities} (and {Epidemiology})},
	url = {https://journals.sagepub.com/doi/epub/10.1177/00754242211019072},
	language = {en},
	urldate = {2023-02-28},
	doi = {10.1177/00754242211019072},
}

@misc{noauthor_mocoda_nodate,
	title = {{MoCoDa} 2},
	url = {https://db.mocoda2.de/c/home},
	urldate = {2022-03-22},
}