Creating a model to summarise a large document


I am wondering if there is an existing KNIME model to summarise a document. I saw this article and can’t figure out how to create something similar.

many thanks for any help.


Hi @dreisner and welcome to the forum.

KNIME has nodes for calculating similarity and distance measures (e.g. Similarity Search) so it maybe possible to do something like this using KNIME nodes, although I’m not aware of any existing workflows that do it. Of course you could also take the existing Python code provide in the article and wrap it in a Python Snippet and try it that way.