Search Results

When two individuals have been linked by a connective, a complex reference object is formed, and subsequent reference by plural anaphors rather than singular ones is preferred. Two reading time and one text change detection study were carried out to examine further the details of the representation of singular and plural objects under these circumstances. The normal conjunction cost associated with subsequently referring to one of the individuals by a singular pronoun is eliminated in circumstances where for the purposes of communication there is nothing to be gained from a singular/plural distinction. The findings fit with current views of shallow, good-enough processing, in which semantic distinctions in mental representations are only made when functionally necessary.

Today, the modular view of sentence processing is unpopular, but the arguments against modularity are not as strong as this apparent consensus would suggest. Almost all experimental investigations of modularity have focused on properties pertaining to information encapsulation, and most of those studies have evaluated just one specific modular architecture. A review of these studies of sentence comprehension suggests that the evidence against information encapsulation is really evidence against that one architecture only, and a whole range of other possible modular architectures remain untested. Although psycholinguistic work has largely ignored the modularity claims relating to shallow outputs, new findings from studies to test “good enough” language processing suggest that the output of the language processing module can be characterized as shallow or minimal. Perhaps, then, the modularity hypothesis was prematurely rejected. Evidence for shallow outputs provides intriguing new support for the idea that sentence processing is indeed modular.

A definition of metacognition as ‘cognition about cognition’ captures neither every aspect of metacognition, nor even its essential aspects. This chapter defends the view that procedural metacognition is a form of activity-dependent processing. Engaging in a task is a precondition for extracting the relevant, context-sensitive metacognitive information; in contrast, metarepresentational attribution does not require such an engagement. Sensitivity to epistemic norms, it is claimed, may manifest itself in an implicit way, through normative guidance appropriate to a first-order task. Two views about normative guidance are discussed. The status of noetic feelings associated with each view is critically examined. An analysis of the ‘ascent routine’ procedure leads us to speculate that, except for ‘hyper-shallow’ forms of self-attributions, agents need to have a background experience of perceptual or memorial evaluation to reliably attribute to themselves the corresponding epistemic contents. Finally four objections are discussed.