Incorporating Connotation of Meaning into Models of Semantic Representation: An Application in Text Corpus Analysis
Shane T. Mueller, Richard M. Shiffrin · eScholarship (California Digital Library) · 2007
Connotation of meaning is an important aspect of human semantic knowledge, and it cannot be captured in simple prototype representations of concepts.Yet models of human episodic memory typically rely on prototype representations, as do statistical techniques for extracting meaningful representations from text corpora (such as LSA).We will demonstrate how REM-II (a model of human episodic and semantic memory) allows connotation of meaning to be represented, and demonstrate that model can be develop and learn reasonable semantic representations by processing the Mindpixel project's 80,000-statement GAC corpus.The success of the model at developing meaningful and contextual representations from a text corpus provides a demonstration of the importance and utility of our assumptions.