spaCy EntityRuler

Natural Language Processing with spaCy

Azadeh Mobasher

Principal Data Scientist

spaCy EntityRuler

EntityRuler adds named-entities to a Doc container
It can be used on its own or combined with EntityRecognizer
Phrase entity patterns for exact string matches (string):

{"label": "ORG", "pattern": "Microsoft"}

Token entity patterns with one dictionary describing one token (list):

{"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}

Adding EntityRuler to spaCy pipeline

Using .add_pipe() method
List of patterns can be added using .add_patterns() method

nlp = spacy.blank("en")
entity_ruler = nlp.add_pipe("entity_ruler")
patterns = [{"label": "ORG", "pattern": "Microsoft"},
            {"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}]
entity_ruler.add_patterns(patterns)

Adding EntityRuler to spaCy pipeline

.ents store the results of an EntityLinker component

doc = nlp("Microsoft is hiring software developer in San Francisco.")
print([(ent.text, ent.label_) for ent in doc.ents])

[('Microsoft', 'ORG'), ('San Francisco', 'GPE')]

EntityRuler in action

Integrates with spaCy pipeline components
Enhances the named-entity recognizer
spaCy model without EntityRuler:

nlp = spacy.load("en_core_web_sm")

doc = nlp("Manhattan associates is a company in the U.S.")
print([(ent.text, ent.label_) for ent in doc.ents])

>>> [('Manhattan', 'GPE'), ('U.S.', 'GPE')]

EntityRuler in action

EntityRuler added after existing ner component:

nlp = spacy.load("en_core_web_sm")
ruler = nlp.add_pipe("entity_ruler", after='ner')
patterns = [{"label": "ORG", "pattern": [{"lower": "manhattan"}, {"lower": "associates"}]}]
ruler.add_patterns(patterns)

doc = nlp("Manhattan associates is a company in the U.S.")
print([(ent.text, ent.label_) for ent in doc.ents])

>>> [('Manhattan', 'GPE'), ('U.S.', 'GPE')]

EntityRuler in action

EntityRuler added before existing ner component:

nlp = spacy.load("en_core_web_sm")
ruler = nlp.add_pipe("entity_ruler", before='ner')
patterns = [{"label": "ORG", "pattern": [{"lower": "manhattan"}, {"lower": "associates"}]}]
ruler.add_patterns(patterns)

doc = nlp("Manhattan associates is a company in the U.S.")
print([(ent.text, ent.label_) for ent in doc.ents])

>>> [('Manhattan associates', 'ORG'), ('U.S.', 'GPE')]

Let's practice!

Natural Language Processing with spaCy