nlp_engine_name: spacy
models:
ner_model_configuration:
  model_to_presidio_entity_mapping:
    PER: PERSON
    PERSON: PERSON
    LOC: LOCATION
    LOCATION: LOCATION
    GPE: LOCATION
    FAC: LOCATION
    ORG: ORGANIZATION
    DATE: DATE_TIME
    TIME: DATE_TIME
    NORP: NRP
    # ja_core_news_lg
    PHONE: PHONE_NUMBER
    # ko_core_news_lg. No reference. Tested manually.
    DT: DATE_TIME
    LC: LOCATION
    OG: ORGANIZATION
    PS: PERSON
    TI: DATE_TIME
    QT: QUANTITY
    # nb_core_news_lg https://github.com/ltgoslo/norne?tab=readme-ov-file#entity-definitions
    EVT: EVENT
    GPE_LOC: LOCATION
    GPE_ORG: ORGANIZATION
    PROD: PRODUCT
    # pl_core_news_lg https://github.com/CLARIN-PL/PolDeepNer?tab=readme-ov-file#about
    date: DATE_TIME
    geogName: LOCATION
    orgName: ORGANIZATION
    persName: PERSON
    placeName: LOCATION
    time: DATE_TIME
    # sv_core_news_lg. No reference. Tested manually.
    PRS: PERSON
    TME: DATE_TIME
    WRK: WORK_OF_ART

  low_confidence_score_multiplier: 0.4
  low_score_entity_names:
    - ORGANIZATION
    - ORG
  default_score: 0.85
  labels_to_ignore:
    - DATE_TIME # Rely on patterns instead
    - LOCATION # Has many false negatives
    - ORGANIZATION # Has many false positives
    - CARDINAL
    - EVENT
    - LANGUAGE
    - LAW
    - MONEY
    - ORDINAL
    - PERCENT
    - PRODUCT
    - QUANTITY
    - WORK_OF_ART
    - MISC # Miscellaneous. Entities which do not belong to the other categories. Animals species for example.
    # ja_core_news_lg
    - MOVEMENT # unknown
    - PET_NAME
    - TITLE_AFFIX # secondary title
    # nb_core_news_lg
    - DRV # Derived. Words derived from a name, but not a name themselves. "NewYorker" for example.
    # sv_core_news_lg
    - MSR # MEASURE (similar to quantity)
    - ENV # unknown, most likely EVENT
    - OBJ # unknown, most likely OBJECT