mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
39 lines
1.7 KiB
Plaintext
39 lines
1.7 KiB
Plaintext
//- 💫 DOCS > USAGE > SPACY 101 > NAMED ENTITIES
|
||
|
||
p
|
||
| A named entity is a "real-world object" that's assigned a name – for
|
||
| example, a person, a country, a product or a book title. spaCy can
|
||
| #[strong recognise] #[+a("/api/annotation#named-entities") various types]
|
||
| of named entities in a document, by asking the model for a
|
||
| #[strong prediction]. Because models are statistical and strongly depend
|
||
| on the examples they were trained on, this doesn't always work
|
||
| #[em perfectly] and might need some tuning later, depending on your use
|
||
| case.
|
||
|
||
p
|
||
| Named entities are available as the #[code ents] property of a #[code Doc]:
|
||
|
||
+code.
|
||
doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')
|
||
|
||
for ent in doc.ents:
|
||
print(ent.text, ent.start_char, ent.end_char, ent.label_)
|
||
|
||
+aside
|
||
| #[strong Text]: The original entity text.#[br]
|
||
| #[strong Start]: Index of start of entity in the #[code Doc].#[br]
|
||
| #[strong End]: Index of end of entity in the #[code Doc].#[br]
|
||
| #[strong Label]: Entity label, i.e. type.
|
||
|
||
+table(["Text", "Start", "End", "Label", "Description"])
|
||
- var style = [0, 1, 1, 1, 0]
|
||
+annotation-row(["Apple", 0, 5, "ORG", "Companies, agencies, institutions."], style)
|
||
+annotation-row(["U.K.", 27, 31, "GPE", "Geopolitical entity, i.e. countries, cities, states."], style)
|
||
+annotation-row(["$1 billion", 44, 54, "MONEY", "Monetary values, including unit."], style)
|
||
|
||
p
|
||
| Using spaCy's built-in #[+a("/usage/visualizers") displaCy visualizer],
|
||
| here's what our example sentence and its named entities look like:
|
||
|
||
+codepen("2f2ad1408ff79fc6a326ea3aedbb353b", 160)
|