Synonyms and Antonyms

NLTK

To find synonyms of a word, lemma can be used. This example is to find synonyms of "cookbook".

>>> syn = wordnet.synsets('cookbook')[0]
>>> lemmas = syn.lemmas
>>> len(lemmas)
2
>>> lemmas
[Lemma('cookbook.n.01.cookbook'), Lemma('cookbook.n.01.cookery_book')]
>>> lemmas[0].name
'cookbook'
>>> lemmas[1].name
'cookery_book'
>>> lemmas[0].synset == lemmas[1].synset
True

As long as seeing this, 'cookbook" and "cookery_book" are put into one synset "cookbook" as lemmas. This logic is to show name of lemmas.

>>> lemmas[1].synset
Synset('cookbook.n.01')
>>> [lemma.name for lemma in syn.lemmas]
['cookbook', 'cookery_book']

This is another example to find synonyms of a word 'book'.

>>> synonyms = []
>>> for syn in wordnet.synsets('book'):
... for lemma in syn.lemmas:
... synonyms.append(lemma.name)
...
>>> len(synonyms)
38

Initialize a variable synonyms then get lemmas of synsets('book'). As a result, there are 38 elements in synonyms. To get entire list of synonyms:

>>> synonyms
['book', 'book', 'volume', 'record', 'record_book', 'book', 'script', 'book', 'p
layscript', 'ledger', 'leger', 'account_book', 'book_of_account', 'book', 'book'
, 'book', 'rule_book', 'Koran', 'Quran', "al-Qur'an", 'Book', 'Bible', 'Christia
n_Bible', 'Book', 'Good_Book', 'Holy_Scripture', 'Holy_Writ', 'Scripture', 'Word
_of_God', 'Word', 'book', 'book', 'book', 'reserve', 'hold', 'book', 'book', 'bo
ok']

It looks some words are duplicated, for example, there are more than 10 'Book' or 'book'. by adding set, get distinct values.

>>> len(set(synonyms))
25
>>> set(synonyms)
set(['record_book', 'Holy_Writ', 'Book', 'Good_Book', 'Scripture', 'script', 'Qu
ran', 'ledger', 'book', 'book_of_account', 'Christian_Bible', 'Bible', 'Word', '
leger', 'Koran', 'playscript', 'hold', 'Word_of_God', 'volume', 'rule_book', 'ac
count_book', 'Holy_Scripture', 'record', "al-Qur'an", 'reserve'])

The number is reduced to 25 and no duplication.

Then try to get antonyms.

>>> gn2 = wordnet.synset('good.n.02')
>>> gn2.definition
'moral excellence or admirableness'
>>> evil = gn2.lemmas[0].antonyms()[0]
>>> evil.name
'evil'
>>> evil.synset.definition
'the quality of being morally wrong in principle or practice'

By using antonyms(), can get antonyms can be displayed. This is another example and easy to understand for non-Enlglish speaking guys like me.

>>> ga1 = wordnet.synset('good.a.01')
>>> ga1.definition
'having desirable or positive qualities especially those suitable for a thing sp
ecified'
>>> bad = ga1.lemmas[0].antonyms()[0]
>>> bad.name
'bad'
>>> bad.synset.definition
'having undesirable or negative qualities'
>>>