Digital Humanities
  • Studies
  • Research
  • Services
  • About us

Digital Texts in Dialogue (2021)

  • Blog
  • Events
  • Projects
    • The Flow
    • Linked Data & Relational Databases – Grounded Knowledge (GeWiS)
    • Text Generator for Style Imitation
    • Economies of Space
    • Confoederatio Ludens
    • BeNASch
    • Bundesratsprotokolle
    • Bit Philology
    • Bullinger digital
  • Services
    • Advice and training on digital tools
    • Support for research projects and applications
    • GameLab
    • Mailing List
    • LOD for Humanities and Social Sciences
    • OMEKA S
    • nodegoat Go: data management and network analysis
    • Open Access Lab
    • Digital Image Processing with IIIF
    • Handwriting and Text Recognition

On this page

  • Online participation & materials
  • Programme
  • Contact
  • Edit this page
  • Report an issue

Digital Texts in Dialogue (2021)

Workshop on digital text processing in the Humanities, with a special focus on Natural Language Processing (NLP)

Event
Author

Digital Humanities (University of Bern)

Published

October 20, 2021

Texts are at the heart of much humanities research. Their digital preparation and processing has therefore become a broad and intensively developed field within the Digital Humanities. Since the introduction of HTML and the World Wide Web, Humanities scholars have been working on the annotation, preparation, and visualisation of textual data in digital environments.

Today, machine-learning methods in Natural Language Processing (NLP) add a new dimension: they enable the extraction of information and the quantitative comparison of texts. In this workshop, we explored current debates and methods with a particular focus on applications for participants’ own research questions. Short expert inputs alternated with hands-on sessions.

Online participation & materials

  • Online participation: https://bit.ly/dig-texte
  • Jupyter Notebook (NLP basics, Google Colab): https://colab.research.google.com/drive/1mH87XpAV01Jgan5meg8aus6WL0XL64Zw?usp=sharing
  • Jupyter Notebook (NLP NER, Google Colab): https://colab.research.google.com/drive/1fQ-vghTxWfN9MG4tr2qcu_yVN5lX3XO5?usp=sharing
  • Slides (Joel Niklaus): https://docs.google.com/presentation/d/1Q2Dy8MQk0j4_hOFOTL3fN8WbCD8WCtGH2j8D-Sf_ubc/edit?usp=sharing
  • Poster (PDF): https://www.dh.unibe.ch/unibe/portal/fak_historisch/fsuf/d_dh/content/e330302/e1404697/e1126780/e1126786/2021_Digitale-Texte-im-Dialog_Poster_ger.pdf

Programme

Time Session Presenter(s)
09:30–10:00 Welcome, introduction, and participant round Organisers
10:00–12:00 From the digital archive to the “Dynarchive” Kurt Fendt
12:00–13:30 Lunch break
13:30–14:00 Swiss-Court-Predict: A Multilingual Legal Judgment Prediction Benchmark Joel Niklaus
14:00–15:30 Hands-on: Introduction to spaCy (NLP framework)
15:30–16:00 Coffee break
16:00–17:00 Parallel hands-on sessions: API harvesting / Using UBELIX Kathi Woitas / Jonas Widmer
from 17:00 Closing (informal)

Contact

For questions, please contact: imdialog@ub.unibe.ch.

Back to top

Reuse

CC BY-SA 4.0
  • Edit this page
  • Report an issue