Publication

Abstract : The present study on word sense disambiguation of Malayalam aims at to understand the causes for lexical ambiguity and finding was to resolve the lexical ambiguity. It has been understood that homonymy and polysemy are the reason for creating ambiguity. Here we are concerned with ambiguity due to homonymy. To resolve the ambiguity we propose two approaches: cluster and deep learning approaches. Certain number of ambiguous words is collected with their occurrence in sentences. Cluster approach is a supervised approach involving POS tagging, lemmatization and sense annotation. The context words are identified for each sense of the experimental ambiguous words. A collocational dictionary is prepared based on this. WSD is implemented using the collocational dictionary. The neural network approach is based on deep learning. It is a corpus driven approach in which the necessary information for disambiguating homonymous words is extracted from the corpus itself. The quantity of the corpus used for WSD decides the accuracy of this approach. © Springer Nature Switzerland AG 2019.