Skip to content

Data are identified incorrectly #8

@denisbnet

Description

@denisbnet

Hi
Could you help with spacy dectctor? We see the different result from piicatcher_spacy and spacy.
Fot test we use the table with one row. We check the same data in https://huggingface.co/spacy/ru_core_news_md
Examples (DatumSpacyDetector):
Column; Value; piicatcher_spacy; spacy
City; Самара; Person; LOC
Address; Самара, ул. Зеленая 20-2; Person; LOC
Last_name; Васильков; Address; No token was detected
Resource; CAREER_SECTION; Person; No token was detected

We use the same spacy mode:

    def __init__(self, model: str = "ru_core_news_md"):
        super(SpacyDetector, self).__init__()

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions