{ "source_file": "CRH 23196688.pdf", "total_replacements": 234, "regex_replacements": 157, "ner_replacements": 16, "sweep_replacements": 61, "entities_found": [ { "original": "10100541860", "replacement": "[CODE_BARRE_1]", "source": "regex", "category": "code_barre" }, { "original": "secr.pneumo@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "sschneider@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "msabatini@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "prigaud@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "cnocent@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "jpmathieu@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "lmasse@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "clethrosne@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "dbonnet@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "eabraham@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "eellie@ch-cotebasque.fr", "replacement": "[EMAIL_11]", "source": "regex", "category": "email" }, { "original": "secr.pneumo@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "sschneider@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "msabatini@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "prigaud@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "cnocent@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "jpmathieu@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "lmasse@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "clethrosne@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "dbonnet@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "eabraham@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "eellie@ch-cotebasque.fr", "replacement": "[EMAIL_11]", "source": "regex", "category": "email" }, { "original": "secr.pneumo@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "sschneider@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "msabatini@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "prigaud@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "cnocent@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "jpmathieu@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "lmasse@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "clethrosne@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "dbonnet@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "eabraham@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "eellie@ch-cotebasque.fr", "replacement": "[EMAIL_11]", "source": "regex", "category": "email" }, { "original": "secr.pneumo@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "sschneider@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "msabatini@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "prigaud@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "cnocent@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "jpmathieu@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "lmasse@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "clethrosne@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "dbonnet@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "eabraham@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "eellie@ch-cotebasque.fr", "replacement": "[EMAIL_11]", "source": "regex", "category": "email" }, { "original": "[MEDECIN", "replacement": "[PERSONNE_1]", "source": "ner", "score": 0.9892317652702332 }, { "original": "[EMAIL", "replacement": "[PERSONNE_2]", "source": "ner", "score": 0.8114061951637268 }, { "original": "[PATIENT_4", "replacement": "[PERSONNE_3]", "source": "ner", "score": 0.885509192943573 }, { "original": "[MEDECIN_30", "replacement": "[PERSONNE_4]", "source": "ner", "score": 0.9088987708091736 }, { "original": "CEMIPLIMAB", "replacement": "[PERSONNE_5]", "source": "ner", "score": 0.8483869433403015 }, { "original": "MEDECIN_", "replacement": "[PERSONNE_6]", "source": "ner", "score": 0.808475136756897 }, { "original": "Dufrois", "replacement": "[MEDECIN]", "source": "ner", "score": 0.9919018745422363 }, { "original": "[PATIENT_", "replacement": "[PERSONNE_7]", "source": "ner", "score": 0.9798977971076965 }, { "original": "[MEDECIN_42", "replacement": "[PERSONNE_8]", "source": "ner", "score": 0.9261439442634583 }, { "original": "[MEDECIN_", "replacement": "[PERSONNE_9]", "source": "ner", "score": 0.9897699356079102 }, { "original": "J. LOEB", "replacement": "[PERSONNE_10]", "source": "ner", "score": 0.9457601308822632 }, { "original": "[MEDECIN_18", "replacement": "[PERSONNE_11]", "source": "ner", "score": 0.9848803877830505 }, { "original": "[MEDECIN_43", "replacement": "[PERSONNE_12]", "source": "ner", "score": 0.9103091955184937 }, { "original": "MEDEC", "replacement": "[PERSONNE_13]", "source": "ner", "score": 0.8166859149932861 }, { "original": "EUSKALDUNA", "replacement": "[PERSONNE_14]", "source": "ner", "score": 0.8862668871879578 }, { "original": "[MEDECIN_2", "replacement": "[PERSONNE_15]", "source": "ner", "score": 0.904394268989563 } ] }