python - 我们如何使用 NTLK 找出句子中的形容词动词副词短语？

Question

下面是来自 StackOverflow 的代码。（它适用于名词短语，但我需要动词、副词、形容词短语）。我是 NLP 新手，对语法规则了解不多。我试图从博客和文档中获得帮助，但无法弄清楚。

此代码块中所需的更改。

NP 块和 VB 块的规则

    NBAR:
        {<NN.*|JJ>*<NN.*>}  # Nouns and Adjectives, terminated with Nouns
        {<RB.?>*<VB.?>*<JJ>*<VB.?>+<VB>?} # Verbs and Verb Phrases

    NP:
        {<NBAR>}
        {<NBAR><IN><NBAR>}  # Above, connected with in/of/etc...

完整代码（它适用于名词短语）

from nltk import word_tokenize, pos_tag
from nltk.corpus import wordnet

from IPython.display import display
lemmatizer = nltk.WordNetLemmatizer()

#word tokenizeing and part-of-speech tagger
document = 'The little brown dog barked at the black cat'
tokens = [nltk.word_tokenize(sent) for sent in [document]]
postag = [nltk.pos_tag(sent) for sent in tokens][0]

# Rule for NP chunk and VB Chunk
grammar = r"""
    NBAR:
        {<NN.*|JJ>*<NN.*>}  # Nouns and Adjectives, terminated with Nouns
        {<RB.?>*<VB.?>*<JJ>*<VB.?>+<VB>?} # Verbs and Verb Phrases

    NP:
        {<NBAR>}
        {<NBAR><IN><NBAR>}  # Above, connected with in/of/etc...

"""
#Chunking
cp = nltk.RegexpParser(grammar)

# the result is a tree
tree = cp.parse(postag)

def leaves(tree):
    """Finds NP (nounphrase) leaf nodes of a chunk tree."""
    for subtree in tree.subtrees(filter = lambda t: t.label() =='NP'):
        yield subtree.leaves()

def get_word_postag(word):
    if pos_tag([word])[0][1].startswith('J'):
        return wordnet.ADJ
    if pos_tag([word])[0][1].startswith('V'):
        return wordnet.VERB
    if pos_tag([word])[0][1].startswith('N'):
        return wordnet.NOUN
    else:
        return wordnet.NOUN

def normalise(word):
    """Normalises words to lowercase and stems and lemmatizes it."""
    word = word.lower()
    postag = get_word_postag(word)
    word = lemmatizer.lemmatize(word,postag)
    return word

def get_terms(tree):    
    for leaf in leaves(tree):
        terms = [normalise(w) for w,t in leaf]
        yield terms

terms = get_terms(tree)

features = []
for term in terms:
    _term = ''
    for word in term:
        _term += ' ' + word
    features.append(_term.strip())
features

标签： pythonmachine-learningdeep-learningnlpnltk