The Role of Metaknowledge in Text Comprehension

In this paper we present an artificial intelligence model of the cognitive processes involved in text comprehension. In particular we focus on the structure of the knowledge required. Our hypothesis is that a relevant feature in the process of text comprehension is the use of specific metaknowledge which correlates the text structure to the intentionality of the author. We introduce three metaknowledge assumptions and show how they can guide the understanding process when the recognition of an unexpected element causes a discrepancy.