Digital Humanities, Computational Linguistics, and Natural Language - PDF document

. . Digital Humanities, Computational Linguistics, and Natural Language Processing Dr.-Ing. Michael Piotrowski Leibniz Institute of European History Uppsala, March 4, 2016 . Defining Digital Humanities Michael Piotrowski 2016-03-04 Digital Humanities, Computational Linguistics, and NLP 1/22 <piotrowski@ieg-mainz.de>

. . Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski interdisciplinary field, a community of practice, or something else again? goals . must commit yourself to some definition. If you want to create a program of studies or devise a research agenda, you Yes, we do. Do we really need a definition? . 2/22 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski WhatIsDigitalHumanities.com 3/22 ▶ However, most definitions focus on methods and say very little about ▶ Related problem: Are the digital humanities a discipline of their own, an

. . Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski (Piotrowski 2012, p. 6) systems (GIS). analytics, data mining, visualization, and geographic information computer-based methods and tools, such as information retrieval, text humanities combine traditional qualitative methods with quantitative, possibilities offered by digital data for humanities research. The digital The emerging field of digital humanities aims to exploit the Piotrowski 2012 4/22 . Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski questions in the humanities computer science humanities and computer science; thus we have two aspects: Relatively broad consensus, that the digital humanities bring together Consensus 5/22 Ⓐ Work on humanities research question using methods and tools from Ⓑ Work on computer science methods und tools for tackling research ➜ Term is inherently ambiguous

. sense. Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski Discussion . 6/22 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski . 7/22 (because it does not use quantitative methods), but it is in the wider creating a digital edition is not digital humanities in the narrow sense does not require the use of quantitative methods). For example, computer-based tools in humanities research (note that this definition In a wider sense , it may also refer to the application of these methods to answer a humanities research question. important point is that it is humanities research, i.e., you’re applying usually complementing traditional qualitative methods […]. The quantitative, computer-based methods for humanities research, In a narrow sense , “digital humanities” refers to the application of Piotrowski 2013 http://nlphist.hypotheses.org/114 ➕ Relatively clearly delimited area of research ➕ Uncontroversal, but not arbitrary ➖ Actually only a description of practices ➖ Nothing is said about motivations or goals of the digital humanities

. Piotrowski 2016 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski creation and use of formal models. These are subfields of their respective disciplines , characterized by the Correspondingly: Digital literary studies, digital philosophy, etc. models. historical circumstances and with the methodology of constructing such Digital history is concerned with the construction of formal models of Definition (Digital history) models in the humanities. The digital humanities study the means and methods of constructing formal Definition (Digital humanities) . . 8/22 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski the humanities ? systematic research (“Erkenntnisgewinn”) Why Digital Humanities? 9/22 ▶ Ultimate goal of all science and scholarship: gaining new insights by ▶ What is the benefit of combining humanities and computer science for ▶ Acceleration of research through digitization? ▶ Automatic analyses of large amounts of data? ▶ Attractive visualizations? ➜ Where is the advancement or “innovation”?

. 2016-03-04 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski narratives are not models, but informal descriptions of models. traditionally not formal and not directly accessible; need to understand its parts and how they interrelate with each other. research. Formal models . 10/22 . Digital Humanities, Computational Linguistics, and NLP Michael Piotrowski The word “formal” means nothing more than Formal models processed and manipulated by computers. (Gladkij & Mel’čuk 1969, p. 9) interested in a degree of formalization that allows models to be logically coherent + unambiguous + explicit. 11/22 ▶ A model is a representation of a selected part of the world. ▶ Model ≈ description ≈ theory ▶ Слово “формальный” не ознацает ничего, кроме как “логически последовательный + однозначный + абсолютно явный”. ▶ There are different degrees of formalization; here we are primarily ▶ All scientific and scholarly research constructs models of their objects of ▶ In order to understand a complex object (phenomenon, situation, …), you ➜ This is exactly what a model describes. ◉ In contrast to the natural sciences, models in the humanities are

. digital humanities subfields. Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski research question and describes the model in a narrative . (on paper or electronically, as text, in spreadsheets, databases, etc.) Traditional research process . 12/22 Digital Humanities, Computational Linguistics, and NLP . Michael Piotrowski 2016-03-04 13/22 models. historical circumstances and with the methodology of constructing such Digital history is concerned with the construction of formal models of Definition (Digital history) for such formal models; thus: a metascience . Digital humanities as a metascience Definition (Digital humanities) their research objects. The digital humanities study the means and methods of constructing formal models in the humanities. ➜ The digital humanities are concerned with the “construction materials” ➜ Individual digital humanities subfields create concrete formal models of ◉ There is no strict boundary between digital humanities and individual Sources Working Materials Narrative ▶ Scholar reads and interprets primary and secondary sources ▶ Facts and insights are recorded as working materials in a variety of forms ▶ Using the working materials, scholar constructs mental model to answer

. 2016-03-04 Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski Where do formal models come into play? . 14/22 . Digital Humanities, Computational Linguistics, and NLP Michael Piotrowski Building on the work of others (traditional process) 15/22 Sources Working Materials Narrative Working Materials Sources Narrative Narrative Sources Formal Model Analysis, Visualization, ...

. Michael Piotrowski Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski Collaboration on a higher level . . Digital Humanities, Computational Linguistics, and NLP 2016-03-04 16/22 17/22 Collaboration on a higher level Narrative Sources Formal Model Analysis, Visualization, ... Narrative Sources Formal Model Analysis, Visualization, ... Narrative Sources Formal Model Analysis, Visualization, ... Narrative Sources Formal Model Analysis, Visualization, ...

. . Digital Humanities, Computational Linguistics, and NLP 2016-03-04 Michael Piotrowski humanities subfields (such as digital history) humanities . because it has essentially completed the transformation from “armchair DH, CL, and NLP linguistics” to an empirical science using formal models 18/22 the humanities. What do we need? Digital Humanities, Computational Linguistics, and NLP 19/22 Michael Piotrowski 2016-03-04 ▶ Humanities research questions and results are primarily qualitative. ▶ Digital humanities are primarily qualitative. ➜ Knowledge representation is central for the creation of formal models in ▶ Linguistics has a “vantage point” for observing the digital humanities, ▶ The role of computational linguistics corresponds to that of digital ▶ The role of corpus linguistics corresponds to that of the digital ▶ Where is the place of NLP? ▶ Applied computational linguistics? ▶ Engineers’ take on linguistics? ▶ Computer science? ▶ Toolsmiths? ▶ What is the role of NLP in digital humanities?