Stanford nlp Stanford NER未正确提取百分比

我试图用斯坦福大学的NER来提取百分比。但它并没有正确地提取百分比

inp_str = 'total revenue received was one hundred and twenty five percent 125% for last financial year'
split_inp_str = inp_str.split()
st = StanfordNERTagger('english.muc.7class.distsim.crf.ser.gz')
print(st.tag(split_inp_str))

这将产生以下输出

[('total', 'O'), ('revenue', 'O'), ('received', 'O'), ('was', 'O'), ('one', 'O'), ('hundred', 'O'), ('and', 'O'), ('twenty', 'O'), ('five', 'PERCENT'), ('percent', 'PERCENT'), ('125%', 'O'), ('for', 'O'), ('last', 'O'), ('financial', 'O'), ('year', 'O')]

---

为什么不提取125%或125%？

你需要标记句子，而不是拆分（）。请尝试以下代码

from nltk import word_tokenize

inp_str = 'total revenue received was one hundred and twenty five percent 125% for last financial year'
split_inp_str = word_tokenize(inp_str)
st = StanfordNERTagger('english.muc.7class.distsim.crf.ser.gz')
print(st.tag(split_inp_str))

当我使用Stanford CoreNLP 3.7.0时，我得到了“125%”的百分比。我正在运行Java代码。如果您使用NLTK，我不能完全确定正在运行什么。