我正在尝试将基于匹配器规则的函数添加到我的 spaCy 管道中。但是,将其添加到管道会导致 StackOverflow 错误。很有可能是用户错误。任何建议或想法将不胜感激。
运行该函数而不将其添加到管道中效果很好。
代码示例:
import spacy
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span
nlp = spacy.load("en_core_web_sm")
def extend_matcher_entities(doc):
matcher = PhraseMatcher(nlp.vocab, attr="SHAPE")
matcher.add("TIME", None, nlp("0305Z"), nlp("1315z"),nlp("0830Z"),nlp("0422z"))
new_ents = []
for match_id, start, end in matcher(doc):
new_ent = Span(doc, start, end, label=nlp.vocab.strings[match_id])
new_ents.append(new_ent)
doc.ents = new_ents
return doc
# Add the component after the named entity recognizer
nlp.add_pipe(extend_matcher_entities, after='ner')
doc = nlp("At 0560z, I walked over to my car and got in to go to the grocery store.")
# extend_matcher_entities(doc)
print([(ent.text, ent.label_) for ent in doc.ents])
这个来自 spacy 代码示例的示例运行良好:
import spacy
from spacy.tokens import Span
nlp = spacy.load("en_core_web_sm")
def expand_person_entities(doc):
new_ents = []
for ent in doc.ents:
if ent.label_ == "PERSON" and ent.start != 0:
prev_token = doc[ent.start - 1]
if prev_token.text in ("Dr", "Dr.", "Mr", "Mr.", "Ms", "Ms."):
new_ent = Span(doc, ent.start - 1, ent.end, label=ent.label)
print(new_ent)
new_ents.append(new_ent)
else:
new_ents.append(ent)
doc.ents = new_ents
print(new_ents)
return doc
# Add the component after the named entity recognizer
nlp.add_pipe(expand_person_entities, after='ner')
doc = nlp("Dr. Alex Smith chaired first board meeting of Acme Corp Inc.")
print([(ent.text, ent.label_) for ent in doc.ents])
我错过了什么?
最佳答案
导致您出现循环引用的违规行是:
matcher.add("TIME", None, nlp("0305Z"), nlp("1315z"),nlp("0830Z"),nlp("0422z"))
将其从函数定义中删除,就可以了:
import spacy
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span
nlp = spacy.load("en_core_web_sm")
pattern = [nlp(t) for t in ("0305Z","1315z","0830Z","0422z")]
def extend_matcher_entities(doc):
matcher = PhraseMatcher(nlp.vocab, attr="SHAPE")
matcher.add("TIME", None, *pattern)
new_ents = []
for match_id, start, end in matcher(doc):
new_ent = Span(doc, start, end, label=nlp.vocab.strings[match_id])
new_ents.append(new_ent)
doc.ents = new_ents
# doc.ents = list(doc.ents) + new_ents
return doc
# Add the component after the named entity recognizer
nlp.add_pipe(extend_matcher_entities, after='ner')
doc = nlp("At 0560z, I walked over to my car and got in to go to the grocery store.")
# extend_matcher_entities(doc)
print([(ent.text, ent.label_) for ent in doc.ents])
[('0560z', 'TIME')]
另请注意,通过 doc.ents = new_ents
您将覆盖之前提取的任何实体
关于python - spaCy - 将扩展函数添加到管道导致堆栈溢出,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/65039857/