Namngiven entitetsigenkänning i transkriberad text

Taligenkänning i Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Installera spaCy

# Install spaCy
$ pip install spacy

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

Använda spaCy

import spacy


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

# Create a spaCy doc
text = ("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.")
doc = nlp(text)

spaCy-tokens

# 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...

spaCy-meningar

# Show sentences in doc
for sentence 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.

spaCy:s namngivna entiteter

Några av spaCy:s inbyggda namngivna entiteter:

PERSON Personer, inklusive fiktiva.
ORG Företag, myndigheter, institutioner osv.
GPE Länder, städer, delstater.
PRODUCT Objekt, fordon, livsmedel osv. (Inte tjänster.)
DATE Absoluta eller relativa datum eller perioder.
TIME Tider kortare än en dag.
MONEY Monetära värden, inklusive enhet.
CARDINAL Siffror som inte tillhör någon annan typ.

spaCy:s namngivna entiteter

# 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

Anpassade namngivna entiteter

# Check spaCy pipeline
print(nlp.pipe_names)

['tok2vec', 'tagger', 'parser',
 'attribute_ruler', 'lemmatizer', 'ner']

Ändra pipelinen

# Add entity_ruler to the pipeline, before ner
ruler = nlp.add_pipe("entity_ruler", before="ner")

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

# Check updated pipeline
nlp.pipe_names

Ändra pipelinen

['tok2vec', 'tagger', 'parser', 'attribute_ruler',
 'lemmatizer', 'entity_ruler', 'ner']

Testa den nya pipelinen

# Recreate the doc with the updated pipeline
doc = nlp(text)

# 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

Nu kör vi och övar på spaCy!

Taligenkänning i Python