A Uniform Model for Generative and Discriminative Commonsense Knowledge Tuples

Abstract

Commonsense knowledge plays a key role in human intelligence. It is knowledge possessed by most humans that helps them in everyday situations. One possible way is to store the knowledge in four types. Each piece is either positive or negative, and generative or discriminative. For efficient retrieval and storage, a uniform model is needed. Existing models for commonsense knowledge are not fit for negative and discriminative knowledge. The aim of this paper is to create a uniform model to store both positive and negative generative and discriminative knowledge tuples. Models are evaluated on a set of generalized queries as well as on the storage they require. Four possible models were evaluated of which two were the most promising: the generative model and the combined model. The generative model is efficient in storage and retrieving generative knowledge for concepts, but relatively slow in distinguishing concepts. Combining the generative model with discriminative tuples gives the combined model, a model that is the most efficient for all queries but expensive in storage. Which of the two models is most suitable depends on the application and the available resources.