RESEARCH.md

Bad Will Hunting

• https://blogs.lse.ac.uk/polis/2022/09/15/bad-will-hunting-the-story-so-far/

• SparkNLP: https://nlp.johnsnowlabs.com/

• Rosette Text Analytics: https://www.rosette.com/capability/entity-extractor/

Selecting articles from a corpus

• https://github.com/asreview/asreview

Tips from Tobias:

• https://maartengr.github.io/BERTopic/index.html#quick-start

• Dimensionality reduction: https://umap-learn.readthedocs.io/en/latest/basic_usage.html

• One-class classification: https://en.wikipedia.org/wiki/One-class_classification

  • Get confidence scores for classification?

• Or: fuzzying out names for other names and see if it can disambiguate

• https://github.com/microsoft/spacy-ann-linker