Integrating Attributional and Distributional Information in a Probabilistic Model of Meaning Representation

In this paper we present models of how meaning is represented in the brain/mind, based upon the assumption that children develop meaning representations for words using two main sources of information: information derived from their concrete experience with objects and events in the world (which we refer to as attributional information) and information implicitly derived from exposure to language (which we refer to as distributional information). In the first part of the paper we present a model developed using self-organising maps (SOMs) starting from speaker-generated features (properties that speakers considered to be important in defining and describing the meaning of a word). This model captures meaning similarity between words based solely upon attributional information and has been shown to be successful in predicting a number of behavioural semantic effects. In the second part of the paper, we present a probabilistic model that goes beyond attributional information alone, integrating this information with distributional information derived from text corpora. The ability of this integrated model to learn semantic relationships is demonstrated with reference to comparable probabilistic models that use only attributional or distributional information.