I have found an issue that might be affecting the performance of the NER model. I am currently using a sort of snippet of the webpage (from the Microsoft search engine) instead of the webpage body content? Check if that is correct (currently, the DB just contains a field named HORUS_SEARCH_RESULT_TEXT.result_description. I don't recall if I am scrapping and saving the body somewhere else to later perform the text classification on it, instead of the description, only.
I have found an issue that might be affecting the performance of the NER model. I am currently using a sort of snippet of the webpage (from the Microsoft search engine) instead of the webpage body content? Check if that is correct (currently, the DB just contains a field named
HORUS_SEARCH_RESULT_TEXT.result_description
. I don't recall if I am scrapping and saving the body somewhere else to later perform the text classification on it, instead of the description, only.