How to use WordNet in Python

WordNet is an English dictionary which is a part of Natural Language Tool Kit (NLTK) for Python. This is an extensive library built to make Natural Language Processing (NLP) easy. Some basic functions will be discussed in this article. To start using WordNet, you have to import it first:

from nltk.corpus import wordnet

Synsets and Lemmas

In WordNet, similar words are grouped into a set known as a Synset (short for Synonym-set). Every Synset has a name, a part-of-speech, and a number. The words in a Synset are known as Lemmas.

Getting Synsets

The function wordnet.synsets('word') returns an array containing all the Synsets related to the word passed to it as the argument.

Example:

print(wordnet.sysnets('room'))

Output:
[Synset(‘room.n.01’), Synset(‘room.n.02’), Synset(‘room.n.03’), Synset(‘room.n.04’), Synset(‘board.v.02’)]

• The method returned five Synsets; four have the name ’room’ and are a nouns, while the last one’s name is ’board’ and is a verb. The output also suggests that the word ‘room’ has a total of five meanings or contexts.

Getting definition of a Synset

By using definition(), a single Synset can further be explored for a definition common to all the Lemmas it contains. This method returns a string, which is the common definition. There are two ways to do this:

1. We can use the array returned by synsets('word') and access one of its elements:

syn_arr = wordnet.synsets('room')
syn_arr[0].definition()

Output :
an area within a building enclosed by walls and floor and ceiling

2. Or, pass the name of the Synset, its part-of-speech and its number, to synset() and then use definition():

wordnet.synset('room.n.02').definition()

Output :
space for movement

Getting all Lemmas of a Synset

Similarly, lemma_names() can be used in two ways to return an array of all Lemma names:

print(syn_arr[1].lemma_names())
# or
print(wordnet.synset('board.v.02').lemma_names())

Output :
[u’room’, u’way’, u’elbow_room’]
[u’board’, u’room’]

Hyponyms

A Hyponym is a specialisation of a Synset. It can be thought of as a child (or derived) class in inheritance. The function hyponyms() returns an array containing all the Synsets which are Hyponyms of the given Synset:

print(wordnet.synset('calendar.n.01').hyponyms())

Output :
[Synset(‘lunar_calendar.n.01’), Synset(‘lunisolar_calendar.n.01’), Synset(‘solar_calendar.n.01’)]

Hypernyms

A Hypernym is a generalisation of a Synset (i.e. the opposite of a Hyponym). An array containing all Hypernyms of a Synset is returned by hypernyms():

print(wordnet.synset('solar_calendar.n.01').hypernyms())

Output :
[Synset(‘calendar.n.01’)]

• Visit NLTK’s official website for more details.