def parse(self, text):
tokens = self.tokenizer.tokenize(text)
intent, probability = self.get_intent(tokens)
entities = get_entities(text, tokens, self.extractor)
if self.ent_synonyms:
Interpreter.replace_synonyms(entities, self.ent_synonyms)
return {
'text': text,
'intent': intent,
'entities': entities,
'confidence': probability
}
def parse(self, text):
"""Parse the input text, classify it and return an object containing its intent and entities."""
intent, probability = self.get_intent(text)
entities = self.get_entities(text)
if self.ent_synonyms:
Interpreter.replace_synonyms(entities, self.ent_synonyms)
return {
'text': text,
'intent': intent,
'entities': entities,
'confidence': probability
}
def test_entity_synonyms():
entities = [{
"entity": "test",
"value": "chines",
"start": 0,
"end": 6
}, {
"entity": "test",
"value": "chinese",
"start": 0,
"end": 6
}, {
"entity": "test",
"value": "china",
"start": 0,
"end": 6
}]
ent_synonyms = {"chines": "chinese", "NYC": "New York City"}
Interpreter.replace_synonyms(entities, ent_synonyms)
assert len(entities) == 3
assert entities[0]["value"] == "chinese"
assert entities[1]["value"] == "chinese"
assert entities[2]["value"] == "china"