Skip to main content
Do you like Artifex? Give it a ⭐ star on GitHub!

named_entity_recognition()

Perform inference with a Named Entity Recognition model, on a single input string or a list of input strings. For each input string, this will return the extracted named entities, which is one or more
of the named entities that the model was trained on.

If no model is loaded, the base Named Entity Recognition model tanaos/tanaos-NER-v1 will be used by default. For more information on what named entities the base Named Entity Recognition model is trained to extract, see the model's Hugging Face page.

Arguments

  • text
    str | list[str]

    A string or a list of strings to extract named entities from. The model will return a list of extracted named entities for each input string.

Response

A list[list[dict]], one list[dict] per input text. For each input text, each list[dict] contains a number of dictionaries, one per named entity extracted from the input text. Each entity's dictionary contains the following keys:

  • entity_group
    str
    : The named entity label predicted by the model.
  • score
    float
    : The confidence score of the prediction, between 0 and 1.
  • word
    str
    : The extracted named entity from the input text.
  • start
    int
    : The starting character index of the extracted named entity in the input text.
  • end
    int
    : The ending character index of the extracted named entity in the
from artifex import Artifex

ner = Artifex().named_entity_recognition

named_entities = ner("John landed in Barcelona at 15:45.")
print(named_entities)
[[{'entity_group': 'PERSON', 'score': 0.92174554, 'word': 'John', 'start': 0, 'end': 4}, {'entity_group': 'LOCATION', 'score': 0.9853817, 'word': ' Barcelona', 'start': 15, 'end': 24}, {'entity_group': 'TIME', 'score': 0.98645407, 'word': ' 15:45.', 'start': 28, 'end': 34}]]