How to use the nltk.corpus.wordnet function in nltk

To help you get started, we’ve selected a few nltk examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github uhh-lt / path2vec / wsd / View on Github external
def convert_to_wordnet_pos(senseval_pos):
    if senseval_pos == 'VERB':
        return wn.VERB
    elif senseval_pos == 'NOUN':
        return wn.NOUN
    elif senseval_pos == 'ADV':
        return wn.ADV
    elif senseval_pos == 'ADJ':
        return wn.ADJ
        return None
github vered1986 / Chirps / source / generate_instances / View on Github external
:param y: the second argument
    :return: Whether they are aligned
    global nlp

    # Allow partial matching
    if fuzz.partial_ratio(' ' + x + ' ', ' ' + y + ' ') == 100:
        return True

    x_words = [w for w in x.split() if not nlp.is_stop(w)]
    y_words = [w for w in y.split() if not nlp.is_stop(w)]

    if len(x_words) == 0 or len(y_words) == 0:
        return False

    x_synonyms = [set([lemma.lower().replace('_', ' ') for synset in wn.synsets(w) for lemma in synset.lemma_names()])
                  for w in x_words]
    y_synonyms = [set([lemma.lower().replace('_', ' ') for synset in wn.synsets(w) for lemma in synset.lemma_names()])
                  for w in y_words]

    # One word - check whether there is intersection between synsets
    if len(x_synonyms) == 1 and len(y_synonyms) == 1 and \
                    len([w for w in x_synonyms[0].intersection(y_synonyms[0]) if not nlp.is_stop(w)]) > 0:
        return True

    # More than one word - align words from x with words from y
    intersections = [len([w for w in s1.intersection(s2) if not nlp.is_stop(w)])
                     for s1 in x_synonyms for s2 in y_synonyms]

    if len([intersection_len for intersection_len in intersections if intersection_len > 0]) >= \
                    0.75 * max(len(x_synonyms), len(y_synonyms)):
        return True
github rapyuta-robotics / rce / ROS_Services / src / Semantics / View on Github external
def create(cls, word1, word2):
        """ Returns a new class instance if word1 and word2 are valid
            words else None is returned.
        # do some checking before creating a _WordPair instance
        if word1 in TermFrequency._FILTER or word2 in TermFrequency._FILTER:
            return None
        word1=wordnet.morphy(word1, wordnet.NOUN)
        word2=wordnet.morphy(word2, wordnet.NOUN)
        if word1 is None or word2 is None:
            return None
        # return the new instance
        return cls(word1, word2)
github JSybrandt / MOLIERE / build_network / src / preprocessXML / View on Github external
def getWordnetPos(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
        elif tag.startswith('S'):
            return wordnet.ADJ
            return None
    res = []
github gsi-upm / sematch / entity-retrieving / View on Github external
def __init__(self):
        self.synsets_list = list(wn.all_synsets())
        self.synset_to_id = { s:s.offset for s in self.synsets_list }
        self.brown_ic = wordnet_ic.ic('ic-brown.dat')
        self.sem_hub = read_json_file("semantic-hub.txt")
        self.sem_hub = {data['offset']:data for data in self.sem_hub}
github gsi-upm / sematch / sematch / View on Github external
def synsets_mapping(self, term):
        return wn.synsets(term, pos=wn.NOUN)
github shubham16394 / Text-Similarity / View on Github external
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
            return None
github ivendrov / order-embeddings-wordnet / View on Github external
from nltk.corpus import wordnet as wn
all_nouns = list(wn.all_synsets('n'))
import numpy as np

# get mapping of synset id to index
id2index = {}
for i in range(len(all_nouns)):
    id2index[all_nouns[i].name()] = i
# get hypernym relations
hypernyms = []
for synset in all_nouns:
    for h in synset.hypernyms() + synset.instance_hypernyms():
        hypernyms.append([id2index[], id2index[]])
hypernyms = np.array(hypernyms)

# save hypernyms
import h5py
github santels / twitter_topic_detection / src / View on Github external
syn2 = self._synsets.get(term2)

        if all(syn is None for syn in (syn1, syn2)):
            syn1, syn2 = self._get_synsets(term1, term2)

        # If one/both synset/s is/are not found in WordNet. If it's not found, its
        # value is None, otherwise, a Synset object.
        if syn1 is None or syn2 is None:
            if syn1 is not None:
                self._synsets[term1] = syn1

            if syn2 is not None:
                self._synsets[term2] = syn2
            return 0

        score = wn.wup_similarity(syn1, syn2)

        if score is None:
            score = 0

        self._synset_pairs[sorted_terms] = score
        return score