hf_ner: Named Entity Recognition (Token Classification)

In huggingfaceR: Access 'Hugging Face' Models and Datasets

Named Entity Recognition (Token Classification)

Description

Extract named entities (people, organizations, locations, etc.) from text using a token-classification model via the Hugging Face Inference Providers API. Returns one row per detected entity, with character offsets that let you highlight or join back to the source text. Inputs that produce no entities (and 'NA' inputs) yield a single row with 'NA' entity fields so every input is represented.

Usage

hf_ner(
  text,
  model = hf_default_model("ner"),
  aggregation_strategy = "simple",
  token = NULL,
  endpoint_url = NULL,
  ...
)

Arguments

text	Character vector of text(s) to analyze.
model	Character string. Model ID from the Hugging Face Hub. Append '":provider"' to select an inference provider. Default: "dslim/bert-base-NER".
aggregation_strategy	Character string. How sub-word tokens are grouped into entities: one of "none", "simple", "first", "average", "max". Default: "simple".
token	Character string or NULL. API token for authentication.
endpoint_url	Character string or NULL. A custom Inference Endpoint URL.
...	Additional arguments (currently unused).

Value

A tibble with columns: text, word, entity_group, score, start, end.

See Also

https://huggingface.co/docs/inference-providers/tasks/token-classification

Examples

## Not run: 
hf_ner("Barack Obama was born in Hawaii.")

# One row per entity, ready to count or join
library(dplyr)
hf_ner(headlines) |>
  filter(!is.na(word)) |>
  count(entity_group, sort = TRUE)

## End(Not run)

huggingfaceR documentation built on Aug. 30, 2026, 1:06 a.m.