A Microfeature Based Approach Towards Metaphor Interpretation

This paper advocates a microfeature based approach towards developing computationalmodels for metaphor interpretation. It is argued that the existing models based on semantic networks and mappings of complex symbolic structures are insu cient and inappropriate for modeling metaphors. A connectionist model of metaphor interpretation based on microfeatures is presented, which tries to take into account some important issues, such as accurate capturing of similarity, automatic formation of features, contextual e ects, elimination of long paths in conceptual hierarchies, salience imbalance, and feature enhancement. Some of these issues have broad implications in cognitive modeling.