'build anthology based on keywords

I tried to use nltk to extract hyponyms for a given list of words, specifically, for some combined words

my code:

 import nltk 
    from nltk.corpus import wordnet as wn
    
    
    list = ['artificial_intelligence', "real_time", 'Big_data', "Internet_of_things", "Healthcare",
            'Fuzzy_logic', 'deep learning', 'Computer_vision', 'machine_learning']


def get_synset(a_list):
    synset_list = []
    for word in a_list:
        a = wn.synsets(word)[:1] #The index is to ensure each word gets assigned 1st synset only
        synset_list.append(a)
    return synset_list


lst_synsets = get_synset(list)
lst_synsets

Here is the output:

 [[Synset('artificial_intelligence.n.01')],
     [Synset('real_time.n.01')],
     [],
     [],
     [Synset('healthcare.n.01')],
     [Synset('fuzzy_logic.n.01')],
     [],
     [],
     []]

I couldn't find NLTK Wordnet Synsets for combined items (e.g. Big data, Internet of things, machine learning, etc) since it doesn't have them.

Is there a way to do that?



Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source