state_data_sources.py 文件源码

def extract_org(sent):
    pos = pos_tag(nltk.tokenize.word_tokenize(sent))
    sentt = nltk.ne_chunk(pos, binary=False)
    org = []
    for subtree in sentt.subtrees(filter=lambda t: t.label() == 'GPE' or t.label() == 'ORGANIZATION'):
        for leave in subtree.leaves():
            org.append(leave)
    return org