spaCy/website/docs/tutorials/rule-based-matcher.jade
2016-10-21 01:00:34 +02:00

62 lines
2.4 KiB
Plaintext

include ../../_includes/_mixins
p.u-text-large spaCy features a rule-matching engine that operates over tokens. The rules can refer to token annotations and flags, and matches support callbacks to accept, modify and/or act on the match. The rule matcher also allows you to associate patterns with entity IDs, to allow some basic entity linking or disambiguation.
+code("python", "Matcher Example").
from spacy.matcher import Matcher
from spacy.attrs import *
import spacy
nlp = spacy.load('en', parser=False, entity=False)
matcher = Matcher(nlp.vocab)
matcher.add_entity(
"GoogleNow", # Entity ID -- Helps you act on the match.
{"ent_type": "PRODUCT", "wiki_en": "Google_Now"}, # Arbitrary attributes (optional)
acceptor=None, # Accept or modify the match
on_match=merge_phrases # Callback to act on the matches
)
matcher.add_pattern(
"GoogleNow", # Entity ID -- Created if doesn't exist.
[ # The pattern is a list of *Token Specifiers*.
{ # This Token Specifier matches tokens whose orth field is "Google"
ORTH: "Google"
},
{ # This Token Specifier matches tokens whose orth field is "Now"
ORTH: "Now"
}
],
label=None # Can associate a label to the pattern-match, to handle it better.
)
doc = nlp(u"I prefer Siri to Google Now.")
matches = matcher(doc)
for ent_id, label, start, end in matches:
print(nlp.strings[ent_id], nlp.strings[label], doc[start : end].text)
entity = matcher.get_entity(ent_id)
print(entity)
matcher.add_pattern(
"GoogleNow",
[ # This Surface Form matches "google now", verbatim, and requires
# "google" to have the NNP tag. This helps prevent the pattern from
# matching cases like "I will google now to look up the time"
{
ORTH: "google",
TAG: "NNP"
},
{
ORTH: "now"
}
]
)
doc = nlp(u"I'll google now to find out how the google now service works.")
matches = matcher(doc)
for ent_id, label, start, end in matches:
print(ent_id, label, start, end, doc[start : end].text)
# Because we specified the on_match=merge_phrases callback,
# we should see 'google now' as a single token.
for token in doc:
print(token.text, token.lemma_, token.tag_, token.ent_type_)