This function takes texts and their corresponding document IDs as inputs, uses the Flair NLP library to extract named entities, and returns a dataframe of the identified entities along with their tags. When no entities are detected in a text, the function returns a data table with NA values. This might clutter the results. Depending on your use case, you might decide to either keep this behavior or skip rows with no detected entities.
Usage
get_entities(
texts,
doc_ids = NULL,
tagger = NULL,
language = NULL,
show.text_id = FALSE,
gc.active = FALSE
)Arguments
- texts
A character vector containing the texts to process.
- doc_ids
A character or numeric vector containing the document IDs corresponding to each text.
- tagger
An optional tagger object. If NULL (default), the function will load a Flair tagger based on the specified language.
- language
A character string indicating the language model to load. Default is "en".
- show.text_id
A logical value. If TRUE, includes the actual text from which the entity was extracted in the resulting data table. Useful for verification and traceability purposes but might increase the size of the output. Default is FALSE.
- gc.active
A logical value. If TRUE, runs the garbage collector after processing all texts. This can help in freeing up memory by releasing unused memory space, especially when processing a large number of texts. Default is FALSE.
Value
A data table with columns:
- doc_id
The ID of the document from which the entity was extracted.
- text_id
If TRUE, the actual text from which the entity was extracted.
- entity
The named entity that was extracted from the text.
- tag
The tag or category of the named entity. Common tags include: PERSON (names of individuals), ORG (organizations, institutions), GPE (countries, cities, states), LOCATION (mountain ranges, bodies of water), DATE (dates or periods), TIME (times of day), MONEY (monetary values), PERCENT (percentage values), FACILITY (buildings, airports), PRODUCT (objects, vehicles), EVENT (named events like wars or sports events), ART (titles of books)
Examples
if (FALSE) { # \dontrun{
library(reticulate)
library(fliaR)
texts <- c("UCD is one of the best universities in Ireland.",
"UCD has a good campus but is very far from
my apartment in Dublin.",
"Essex is famous for social science research.",
"Essex is not in the Russell Group, but it is
famous for political science research.",
"TCD is the oldest university in Ireland.",
"TCD is similar to Oxford.")
doc_ids <- c("doc1", "doc2", "doc3", "doc4", "doc5", "doc6")
# Load NER ("ner") model
tagger_ner <- load_tagger_ner('ner')
results <- get_entities(texts, doc_ids, tagger_ner)
print(results)} # }