KeyBERT

Interessante tecnica per l'estrazione delle parole chiave da un testo, che consiste in (quote direttamente dall'implementazione):

A minimal method for keyword extraction with BERT

The keyword extraction is done by finding the sub-phrases in

a document that are the most similar to the document itself.

First, document embeddings are extracted with BERT to get a

document-level representation. Then, word embeddings are extracted

for N-gram words/phrases. Finally, we use cosine similarity to find the

words/phrases that are the most similar to the document.

The most similar words could then be identified as the words that

best describe the entire document.

Collegamenti

https://github.com/MaartenGr/KeyBERT?tab=readme-ov-file

https://towardsdatascience.com/keyword-extraction-with-bert-724efca412ea