SemanticNet-Perception of Human Pragmatics
Amitava Das, Sivaji Bandyopadhyay · 2010
SemanticNet is a semantic network of lexicons to hold human pragmatic knowledge. So far Natural Language Processing (NLP) research patronized much of manually augmented lexicon resources such as WordNet. But the small set of semantic relations like Hypernym, Holonym, Meronym and Synonym etc are very narrow to capture the wide variations human cognitive knowledge. But no such information could be retrieved from available lexicon resources. SemanticNet is the attempt to capture wide range of context dependent semantic inference among various themes which human beings perceive in their pragmatic knowledge, learned by day to day cognitive interactions with the surrounding physical world. SemanticNet holds human pragmatics with twenty well established semantic relations for every pair of lexemes. As every pair of relations cannot be defined by fixed number of certain semantic relation labels thus additionally contextual semantic affinity inference in SemanticNet could be calculated by network distance and represented as a probabilistic score. SemanticNet is being presently developed for Bengali language.