Some libraries like node-nlp allow defining detection threshold for NER. For instance spederman can be matched as spiderman. Is it possible in compromise because in some cases it can be too strict?
hi @torava yes, we make the assumption that the text is always correct.
maybe this should be added to the docs somewhere.
.topics() will return only people+places+organizations.
Some libraries like node-nlp allow defining detection threshold for NER. For instance spederman can be matched as spiderman. Is it possible in compromise because in some cases it can be too strict?