Word Net is a semantically oriented dictionary of English, similar to a traditional thesaurus but with a richer structure.
WordNet is a part of NLTK and you will use wordnet later in this module to identify the ‘correct’ sense of a word (i.e. for word sense disambiguation).
Another important resource for semantic processing is ConceptNet which deals specifically with assertions between concepts . for example, there is the concept of a “dog” ,and the concept of a “kennel” .As a human , we know that a dog lives inside a kennel. ConceptNet record that assertion with/c/en /dog/r/Atlocation/c/en/ kennel.
Conceptnet is a representation that provides commonsense linkages between words. for example, it states that bread is commonly found near toasters. these everyday facts could be useful if , for e.g., you wanted to make a smart chatbot which says-“Since you like toasters, do also like bread? I can order some for you.”
But, unfortunately, Conceptnet isn’t organized as well as on would want. for instance, it explicitly states that a toaster is related to an automobile. this is true since they are both mechanical machines, but you wouldn’t want for e.g. a chatbot to learn that relationship in most contexts.