Insurance data science : Text

At the Summer School of the Swiss Association of Actuaries, in Lausanne, I will start talking about text based data and NLP this Thursday. Slides are available online

Ewen Gallic (AMSE) will present a tutorial on tweets. I can upload a few additional slides on LSTM (recurrent neural nets)



Cite this blog post
Arthur Charpentier (2019, August 14). Insurance data science : Text. Freakonometrics. Retrieved May 18, 2024, from https://doi.org/10.58079/ovds

2 thoughts on “Insurance data science : Text”

  1. Thanks for sharing.

    FYI. You might also be interested in using udpipe (https://bnosac.github.io/udpipe/en/) for parsing: e.g. visualisation at https://github.com/bnosac/udpipe/issues/59 or in incorporating traditional sequence models in your course (https://cran.r-project.org/web/packages/crfsuite/index.html) or in incorporating advanced embedding techniques (https://cran.r-project.org/web/packages/ruimtehol/index.html – this package unfortunately seems not to work on Mac however)

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.