HiDEx: The High Dimensional Explorer

INTRODUCTION In this chapter we present a new tool for exploring a class of models of lexical semantics derived from HAL (Hyperspace Analog to Language; Burgess, 1998; Burgess & Lund, 2000), a computational model of word meaning that derives semantic relationships from lexical co-occurrence. Although the original HAL model was well specified, it contains several parameters whose values were set without formal or empirical justification. Our freely available implementation of the class of HAL-derived models is called the High Dimensional Explorer (HiDEx). HiDEx allows users to systematically vary its defining parameters, creating models that are algorithmically identical, but parameterized differently. In this paper we will explain how HiDEx works, and how we have been able to use it to explore HAL's parameter space. ABSTRACT HAL (Hyperspace Analog to Language) is a high-dimensional model of semantic space that uses the global co-occurrence frequency of words in a large corpus of text as the basis for a representation of semantic memory. In the original HAL model, many parameters were set without any a priori rationale. In this chapter we describe a new computer application called the High Dimensional Explorer (HiDEx) that makes it possible to systematically alter the values of the model's parameters and thereby to examine their effect on the co-occurrence matrix that instantiates the model. New parameter sets give us measures of semantic density that improve the model's ability to predict behavioral measures. Implications for such models are discussed.