Reconnaissance d'entités nommées sur du texte transcrit

Traitement de la langue parlée en Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Installer spaCy

# Install spaCy
$ pip install spacy

# Download spaCy language model
$ python -m spacy download en_core_web_sm

Utiliser spaCy

import spacy


# Load spaCy language model
nlp = spacy.load("en_core_web_sm")

# Create a spaCy doc
doc = nlp("I'd like to talk about a smartphone I ordered on July 31st from your 
Sydney store, my order number is 40939440. I spoke to Georgia about it last week.")

Jetons spaCy

# Show different tokens and positions
for token in doc:
  print(token.text, token.idx)

I 0
'd 1
like 4
to 9
talk 12
about 17
a 23
smartphone 25...

Phrases spaCy

# Show sentences in doc
for sentences in doc.sents:
  print(sentence)

I'd like to talk about a smartphone I ordered on July 31st from your Sydney store, 
my order number is 4093829.
I spoke to one of your customer service team, Georgia, yesterday.

Entités nommées spaCy

Quelques entités nommées intégrées de spaCy :

PERSON Personnes, y compris fictives.
ORG Entreprises, organismes, établissements, etc.
GPE Pays, villes, États/provinces.
PRODUCT Objets, véhicules, aliments, etc. (pas les services)
DATE Dates ou périodes absolues ou relatives.
TIME Heures ou durées inférieures à une journée.
MONEY Valeurs monétaires, avec unité.
CARDINAL Nombres qui ne relèvent d'aucun autre type.

Entités nommées spaCy

# Find named entities in doc
for entity in doc.ents:
  print(entity.text, entity.label_)

July 31st DATE
Sydney GPE
4093829 CARDINAL
one CARDINAL
Georgia GPE
yesterday DATE

Entités nommées personnalisées

# Import EntityRuler class
from spacy.pipeline import EntityRuler

# Check spaCy pipeline
print(nlp.pipeline)

[('tagger', <spacy.pipeline.pipes.Tagger at 0x1c3aa8a470>),
 ('parser', <spacy.pipeline.pipes.DependencyParser at 0x1c3bb60588>),
 ('ner', <spacy.pipeline.pipes.EntityRecognizer at 0x1c3bb605e8>)]

Modifier le pipeline

# Create EntityRuler instance
ruler = EntityRuler(nlp)

# Add token pattern to ruler
ruler.add_patterns([{"label":"PRODUCT", "pattern": "smartphone"}])

# Add new rule to pipeline before ner
nlp.add_pipe(ruler, before="ner")

# Check updated pipeline
nlp.pipeline

Modifier le pipeline

[('tagger', <spacy.pipeline.pipes.Tagger at 0x1c1f9c9b38>),
 ('parser', <spacy.pipeline.pipes.DependencyParser at 0x1c3c9cba08>),
 ('entity_ruler', <spacy.pipeline.entityruler.EntityRuler at 0x1c1d834b70>),
 ('ner', <spacy.pipeline.pipes.EntityRecognizer at 0x1c3c9cba68>)]

Tester le nouveau pipeline

# Test new entity rule
for entity in doc.ents:
    print(entity.text, entity.label_)

smartphone PRODUCT
July 31st DATE
Sydney GPE
4093829 CARDINAL
one CARDINAL
Georgia GPE
yesterday DATE

Lançons-nous et pratiquons spaCy !

Traitement de la langue parlée en Python