Frequency, activation, and the production of verb inflection in agrammatic aphasia

Background: The production of verb inflectional morphology has been shown to be differentially impaired in agrammatic aphasia: agreement is preserved relative to tense. The consistency with which this pattern has been observed across a wide range of typologically diverse languages should be viewed as surprising, given that language-specific characteristics have been demonstrated to correlate with differences in agrammatic performance on various grammatical constructions. In addition, the preservation of agreement, a primarily syntactic inflection, over tense, a semantic inflection, appears to run counter to previous research showing impairments of syntactic processing in agrammatic aphasia. Representational and processing-based accounts have attempted to explain the dissociation of agreement and tense morphology in agrammatic speech, but have neglected these two points.Aims: The purpose of this review is to investigate the degree to which current theories can account for the differential impairment of agreement and tense, and to propose a new theory that is situated in the larger context of language production models. Discussion will explore the role of frequency and the activation effects of elements that frequently co-occur during language production. Based on this review, the Grammatical Encoding Co-Occurrence (GECO) Frequency Hypothesis will be proposed. This hypothesis attributes the preservation of agreement over tense to the co-occurrence of grammatical features at the stage of language production when inflectional morphology is encoded. Main Contribution: The GECO Frequency Hypothesis accounts for the preservation of agreement relative to tense in the context of cross-linguistic differences by making reference to aspects of inflectional morphology and language production that are common across languages. It is compatible with the results obtained from previous studies, and adds precision and clarity to the previous accounts of the differential impairment of agreement and tense. More generally, the hypothesis contributes to an understanding of the role of frequency at different stages in language production. Implications of the GECO Frequency Hypothesis for both agrammatic and normal language production include that language production is an activation-based process rather than one involving syntactic operations per se.Conclusions: The differential impairment of agreement and tense morphology in agrammatic aphasia is a result of the co-occurrence frequency of grammatical features activated during the language production process, rather than impairments to specific morphological representations or syntactic processes.