generate_ngram_pos_link.py 文件源码

def getPOSLinks(text):
    wordnet_lemmatizer = WordNetLemmatizer()
    text = nltk.word_tokenize(text)
    pos = nltk.pos_tag(text)
    links = []
    link = []
    active = False
    for w in pos:
        part = w[1]
        word = w[0]
        if(not active and (part[:2] == "DT" or part == "WP" or part == "VB" or part == "IN")):
            active = True
        if(active):
            link.append(wordnet_lemmatizer.lemmatize(word))
        #extract main body
        if(active and (part == "PRP" or part[:2] == "NN" or part == "." )):
            active = False
            links.append(" ".join(link))
            link = []
    return links