如何在spaCy中添加要标记化的特定子字符串？

import spacy
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span

nlp = spacy.load('en_core_web_sm')

matcher = PhraseMatcher(nlp.vocab)

substrings = ['特定子字符串1', '特定子字符串2', '特定子字符串3']

patterns = [nlp(text) for text in substrings]

matcher.add('CUSTOM_ENTITIES', None, *patterns)

def custom_tokenizer(doc):
    matches = matcher(doc)
    spans = [Span(doc, start, end, label='CUSTOM_ENTITY') for match_id, start, end in matches]
    doc.ents = spans
    return doc

nlp.add_pipe(custom_tokenizer, after='ner')