This system allows for the extraction of keywords from any sentence based on "Lexical Centrality Theory." Unlike version Lunaris 1.5 to search for the best words, this version uses global attention to words (a bit like BERT; it's bidirectional). This means the model takes context into account to find the best keywords. Both systems must be approved by the Ametrine team, although for me this version is slightly better, but at the cost of significantly higher computational effort (yes, for a 15-word sentence, it requires 15^2 calculations here, compared to 15 for version Lunaris 1.5). AmetrineOS - Lunaris 1.5 Keyword Extractor : https://scratch.mit.edu/projects/1378293727/
