As with machine learing problems, lack of labelled data is a common problem in building disambiguation models.Thus ,we need unsupervised techniquesto solve the same problem.
A popular unsupervised algorithm used for word sense disambiguation is the Lerk algorithm.
there are various ways in which you can usethe lesk algorithm. Apart from what the professor has discussed,you can just take the definitions corresponding to the different senses of the ambiguous wordand see which definition overlaps maximum with the neighbouring words of the ambiguous word.The sense which has the maximum overlap with the surrounding words is then chosen as the ‘correct sense’.
Let’s now use lesk algorithm to disambiguate the word ‘bank‘ in a text.
Recall that WordNet has a network of synonyms called synset for individual words.