Introduction to Statistical Semantics

Abstract

Human beings create meaning from the fact that concepts tend to occur together in a predictable way. When we see a dog, we also see a tail, paws, eyes, legs, fur, and etcetera. In this context, we would see an owner who goes for a walk in the park with the dog that is attached to a leach, and the dog might bark. Thus, the concept of a dog is connected with these other concepts, and when these concepts reliable co-occur with each other, then the meaning of what a dog is, is then created. In other words, the meaning of a concept is generated when there are reliable relationships between different concepts related to the one we want to define. Thus, the probability of occurrences of one concept is increased by the presence of another concept. Nevertheless, despite the fact that the world is filled with reliable co-occurrences that provide opportunities to the creation of meaning, it is not sufficient in itself to create meaning. Meaning creation also requires a mental representation that reflects the co-occurrences that are present in the world. This is what happens in the brain when we apprehend our environment. Sadly, we do not have a direct access to the brain’s representation of meaning. In this book, different authors outline scientific research that use statistical semantics as a method to create models for describing semantic representations of human’s meaning-making through natural language.