Notebooks in Education

Computational notebooks (in short notebooks) provide a popular environment for literate programming, especially in education contexts. This also applies to Natural Language Processing (

Natural Language Processing

See: http://en.wikipedia.org/wiki/Natural_language_processing

). On this page, a first overview is provided of the use of Notebooks in connection with the CLARIN infrastructure.

Notebooks Provided by CLARIN Centres

• LINDAT/CLARIAH-CZ: 
  • POS Tagging and Lemmatization (Czech model)
  • Sentiment Analysis (Czech Model)
• SAFMORIL:
  • Online tutorial for Computational Morphology with HFST
  • Source Code repository on github
• ILC4CLARIN:
  • SSHOC Data Stewardship terminology and Metadata SKOSifying mapping
• PORTULAN CLARIN:
  • Tokenization: Segmentation of texts into lexical tokens.
  • Syllabification: Syllabification of expressions.
  • Sentence splitting: Segmentation of texts into sentences and paragraphs.
  • UPOS tagging: Tokenization and morphosyntactic tagging of expressions in texts with Universal Dependencies POS tagset.
  • LXPOS tagging: Tokenization and morphosyntactic tagging of expressions in texts with LX POS tagset.
  • UÉvoraPOS tagging: Tokenization and morphosyntactic tagging of expressions in texts with UÉvora POS tagset.
  • Universal Sub-syntactic analysis: Tokenization, lemmatization, inflection analysis and morphosyntactic tagging of expressions in texts within the Universal Dependencies framework.
  • LX Sub-syntactic analysis: Tokenization, lemmatization, inflection analysis and morphosyntactic tagging of expressions in texts within the LX framework.
  • Named entity recognition: Detection and semantic classification of names in texts.
  • Universal Dependency parsing: Analysis of grammatical functions in sentences within Universal Dependencies framework.
  • LX Dependency parsing: Analysis of grammatical functions in sentences within LX framework.
  • Constituency parsing: Analysis of syntactic constituents in sentences.
  • Grammatical quantitative analysis: Occurrence counting of grammatical elements in texts.
  • Machine Translation: Translation of a sentence from a source language to a target language (Portuguese-Chinese).

Notebooks for Processing Europeana Newspaper Collections

Jupyter notebooks for Europeana newspaper text resource processing with CLARIN NLP tools:

• SSHOC Marketplace entry about this tutorial
• Notebooks on github
• Introductory screencast presenting the resources and the notebooks

• Tutorial slides:

  20220615-newspapers_and_jupyter_notebooks_slides.pdf
• Candela, G., Chambers, S., & Sherratt, T. (2023). An approach to assess the quality of Jupyter projects published by GLAM institutions. Journal of the Association for Information Science and Technology, 1–15. https://doi.org/10.1002/asi.24835