Skip to content
Related Articles

Related Articles

NLP | Synsets for a word in WordNet
  • Last Updated : 28 Jan, 2019

WordNet is the lexical database i.e. dictionary for the English language, specifically designed for natural language processing.

Synset is a special kind of a simple interface that is present in NLTK to look up words in WordNet. Synset instances are the groupings of synonymous words that express the same concept. Some of the words have only one Synset and some have several.

Code #1 : Understanding Synset




from nltk.corpus import wordnet
syn = wordnet.synsets('hello')[0]
  
print ("Synset name :  ", syn.name())
  
# Defining the word
print ("\nSynset meaning : ", syn.definition())
  
# list of phrases that use the word in context
print ("\nSynset example : ", syn.examples())

Output:

Synset name :   hello.n.01

Synset meaning :  an expression of greeting

Synset example :  ['every morning they exchanged polite hellos']

wordnet.synsets(word) can be used to get a list of Synsets. This list can be empty (if no such word is found) or can have few elements.
 
Hypernyms and Hyponyms –



Hypernyms: More abstract terms
Hyponyms: More specific terms.

Both come to picture as Synsets are organized in a structure similar to that of an inheritance tree. This tree can be traced all the way up to a root hypernym. Hypernyms provide a way to categorize and group words based on their similarity to each other.

Code #2 : Understanding Hypernerms and Hyponyms




from nltk.corpus import wordnet
syn = wordnet.synsets('hello')[0]
  
print ("Synset name :  ", syn.name())
  
print ("\nSynset abstract term :  ", syn.hypernyms())
  
print ("\nSynset specific term :  "
       syn.hypernyms()[0].hyponyms())
  
syn.root_hypernyms()
  
print ("\nSynset root hypernerm :  ", syn.root_hypernyms())

Output:

Synset name :   hello.n.01

Synset abstract term :   [Synset('greeting.n.01')]

Synset specific term :   [Synset('calling_card.n.02'), Synset('good_afternoon.n.01'), 
Synset('good_morning.n.01'), Synset('hail.n.03'), Synset('hello.n.01'), 
Synset('pax.n.01'), Synset('reception.n.01'), Synset('regard.n.03'), 
Synset('salute.n.02'), Synset('salute.n.03'), Synset('welcome.n.02'), 
Synset('well-wishing.n.01')]

Synset root hypernerm :   [Synset('entity.n.01')]


 
Code #3 : Part of Speech (POS) in Synset.




syn = wordnet.synsets('hello')[0]
print ("Syn tag : ", syn.pos())
  
syn = wordnet.synsets('doing')[0]
print ("Syn tag : ", syn.pos())
  
syn = wordnet.synsets('beautiful')[0]
print ("Syn tag : ", syn.pos())
  
syn = wordnet.synsets('quickly')[0]
print ("Syn tag : ", syn.pos())

Output:

Syn tag :  n
Syn tag :  v
Syn tag :  a
Syn tag :  r

machine-learning

My Personal Notes arrow_drop_up
Recommended Articles
Page :