Python wordnet.VERB属性代码示例

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def pos_tag_text(text):
    
    def penn_to_wn_tags(pos_tag):
        if pos_tag.startswith('J'):
            return wn.ADJ
        elif pos_tag.startswith('V'):
            return wn.VERB
        elif pos_tag.startswith('N'):
            return wn.NOUN
        elif pos_tag.startswith('R'):
            return wn.ADV
        else:
            return None
    
    tagged_text = tag(text)
    tagged_lower_text = [(word.lower(), penn_to_wn_tags(pos_tag))
                         for word, pos_tag in
                         tagged_text]
    return tagged_lower_text
    
# lemmatize text based on POS tags 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def pos_tag_convert_penn_to_wn(tag):
    """
    Convert POS tag from Penn tagset to WordNet tagset.

    :param tag: a tag from Penn tagset
    :return: a tag from WordNet tagset or None if no corresponding tag could be found
    """
    from nltk.corpus import wordnet as wn

    if tag in ['JJ', 'JJR', 'JJS']:
        return wn.ADJ
    elif tag in ['RB', 'RBR', 'RBS']:
        return wn.ADV
    elif tag in ['NN', 'NNS', 'NNP', 'NNPS']:
        return wn.NOUN
    elif tag in ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
        return wn.VERB
    return None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def get_wordnet_pos(self,treebank_tag):
        """
        return WORDNET POS compliance to WORDENT lemmatization (a,n,r,v) 
        """

        if treebank_tag.startswith('J'):
            return wordnet.ADJ

        elif treebank_tag.startswith('V'):
            return wordnet.VERB

        elif treebank_tag.startswith('N'):
            return wordnet.NOUN

        elif treebank_tag.startswith('R'):
            return wordnet.ADV

        else:
            return wordnet.NOUN 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def _pos_tuples():
    return [
        (wn.NOUN,'N','noun'),
        (wn.VERB,'V','verb'),
        (wn.ADJ,'J','adj'),
        (wn.ADV,'R','adv')] 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def wup_similarity(tagx, tagy):
    scores = []
    for pos in [wn.NOUN, wn.VERB, wn.ADJ, wn.ADJ_SAT, wn.ADV]:
        try:
            synsetx = wn.synset('%s.%s.01' % (tagx,pos))
            synsety = wn.synset('%s.%s.01' % (tagy,pos))
            score = synsetx.wup_similarity(synsety)
            if score is None:
                score = 0
        except Exception, e:
            score = 0
        scores.append(score) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def test_pos_tag_convert_penn_to_wn():
    assert pos_tag_convert_penn_to_wn('JJ') == wn.ADJ
    assert pos_tag_convert_penn_to_wn('RB') == wn.ADV
    assert pos_tag_convert_penn_to_wn('NN') == wn.NOUN
    assert pos_tag_convert_penn_to_wn('VB') == wn.VERB

    for tag in ('', 'invalid', None):
        assert pos_tag_convert_penn_to_wn(tag) is None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def __get_wordnet_pos(self, treebank_tag):

        if treebank_tag.startswith("J"):
            return wordnet.ADJ
        elif treebank_tag.startswith("V"):
            return wordnet.VERB
        elif treebank_tag.startswith("N"):
            return wordnet.NOUN
        elif treebank_tag.startswith("R"):
            return wordnet.ADV
        else:
            return "" 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def tagwn(self, tag):
        """
        Returns the WordNet tag from the Penn Treebank tag.
        """
        return {
            'N': wn.NOUN,
            'V': wn.VERB,
            'R': wn.ADV,
            'J': wn.ADJ
        }.get(tag[0], wn.NOUN) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def get_wordnet_pos(treebank_tag):
        """ Converts a Penn Tree-Bank part of speech tag into a corresponding WordNet-friendly tag. 
        Borrowed from: http://stackoverflow.com/questions/15586721/wordnet-lemmatization-and-pos-tagging-in-python. """
        if treebank_tag.startswith('J') or treebank_tag.startswith('A'):
            return wordnet.ADJ
        elif treebank_tag.startswith('V'):
            return wordnet.VERB
        elif treebank_tag.startswith('N'):
            return wordnet.NOUN
        elif treebank_tag.startswith('R'):
            return wordnet.ADV
        else:
            return 'OTHER' 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def convert_to_wn_pos(pos):
    if pos.startswith("J"):
        return wn.ADJ
    elif pos.startswith("V"):
        return wn.VERB
    elif pos.startswith("N"):
        return wn.NOUN
    elif pos.startswith("R"):
        return wn.ADV
    else:
        return "" 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def get_word_net_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def lemmatize(self, token, pos_tag):
        tag = {
            'N': wn.NOUN,
            'V': wn.VERB,
            'R': wn.ADV,
            'J': wn.ADJ
        }.get(pos_tag[0], wn.NOUN)

        return self.lemmatizer.lemmatize(token, tag) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def wnpos(tag):
    # Return the WordNet POS tag from the Penn Treebank tag
    return {
        'N': wn.NOUN,
        'V': wn.VERB,
        'R': wn.ADV,
        'J': wn.ADJ
    }.get(tag[0], wn.NOUN) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import VERB [as 别名]
def _sentence_to_mongo(typ, items):
    import nltk
    from nltk.corpus import wordnet

    def wordnet_pos(tag):
        if tag.startswith('J'):
            return wordnet.ADJ
        elif tag.startswith('V'):
            return wordnet.VERB
        elif tag.startswith('N'):
            return wordnet.NOUN
        elif tag.startswith('R'):
            return wordnet.ADV
        else:
            return wordnet.NOUN

    # nltk.download('punkt')
    nltk.download('averaged_perceptron_tagger')
    nltk.download('stopwords')
    nltk.download('wordnet')
    nltk.download('punkt')
    stop_words = set(nltk.corpus.stopwords.words('english'))
    stemmer = nltk.stem.WordNetLemmatizer()
    sentences = []
    for trans in items:
        eng, chn = trans.getsource(), trans.gettarget()
        tokens = nltk.word_tokenize(eng)
        pos_tag = [pos[1] for pos in nltk.pos_tag(tokens)]
        roots = [stemmer.lemmatize(word, wordnet_pos(pos_tag[idx])) for idx, word in enumerate(tokens)]
        cleanword = [token for token in roots if token.isalpha() and token not in stop_words and len(token) >= 3]
        # remove duplicates
        clean_word = list(dict.fromkeys(cleanword))
        if len(clean_word) > 0:
            score = Word.search_words(*clean_word).sum('star') / len(clean_word)
        else:
            score = -1
        sentence = Sentence(eng=eng, chn=chn, words=tokens, pos_tag=pos_tag, roots=roots, score=score, typ=typ)
        sentences.append(sentence)
        if len(sentences) > 50:
            Sentence.objects.insert(sentences)
            sentences = []