Keyword extraction — statistical and vocabulary-controlled
KeyBERT · YAKE · KER · AMČR and TEATER
Extraction of statistical and vocabulary-controlled keywords from text-containing documents, with the method and score of every keyword.
Keywords of both kinds, kept apart. Reads the record after nlp-enrich.
Where this sits in the pipeline
- page-classification
- →
- ocr-postprocess
- →
- translator
- →
- nlp-enrich
- →
- keyword-extract
- →
- digital-convert