generate_distractors_wordnet.py

# -*- coding: utf-8 -*-
"""Generate_Distractors_Wordnet.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/107-wTgLfxq-rJVYm8uEvV57bK2vO9Tw2
"""

import nltk
nltk.download('wordnet')
from nltk.corpus import wordnet as wn

def get_distractors_wordnet(syn,word):
    distractors=[]
    word= word.lower()
    orig_word = word
    if len(word.split())>0:
        word = word.replace(" ","_")
    hypernym = syn.hypernyms()
    if len(hypernym) == 0: 
        return distractors
    for item in hypernym[0].hyponyms():
        name = item.lemmas()[0].name()
        #print ("name ",name, " word",orig_word)
        if name == orig_word:
            continue
        name = name.replace("_"," ")
        name = " ".join(w.capitalize() for w in name.split())
        if name is not None and name not in distractors:
            distractors.append(name)
    return distractors

def get_wordsense(sent,word):
    word= word.lower()
    if len(word.split())>0:
        word = word.replace(" ","_")
    synsets = wn.synsets(word,'n')
    if synsets:
        wup = max_similarity(sent, word, 'wup', pos='n')
        adapted_lesk_output =  adapted_lesk(sent, word, pos='n')
        lowest_index = min (synsets.index(wup),synsets.index(adapted_lesk_output))
        return synsets[lowest_index]
    else:
        return None