Grammatical analysis as a distributed neurobiological function

Abstract

Language processing engages large-scale functional networks in both hemispheres. Although it is widely accepted that left perisylvian regions have a key role in supporting complex grammatical computations, patient data suggest that some aspects of grammatical processing could be supported bilaterally. We investigated the distribution and the nature of grammatical computations across language processing networks by comparing two types of combinatorial grammatical sequences--inflectionally complex words and minimal phrases--and contrasting them with grammatically simple words. Novel multivariate analyses revealed that they engage a coalition of separable subsystems: inflected forms triggered left-lateralized activation, dissociable into dorsal processes supporting morphophonological parsing and ventral, lexically driven morphosyntactic processes. In contrast, simple phrases activated a consistently bilateral pattern of temporal regions, overlapping with inflectional activations in L middle temporal gyrus. These data confirm the role of the left-lateralized frontotemporal network in supporting complex grammatical computations. Critically, they also point to the capacity of bilateral temporal regions to support simple, linear grammatical computations. This is consistent with a dual neurobiological framework where phylogenetically older bihemispheric systems form part of the network that supports language function in the modern human, and where significant capacities for language comprehension remain intact even following severe left hemisphere damage.

Keywords: brain; computation; grammar; hemispheric distribution.

Figure 1

Significant activation for lexical processing (all words minus MuR), rendered onto the surface of a canonical brain. Clusters thresholded at P < 0.05 FDR corrected for multiple comparisons.

Figure 2

a) Activation RDM from L BA44: 12 × 12 matrix of correlation distances (one minus the correlation value) between activation patterns for each pair of conditions. RDMs are symmetrical across the diagonal. b) Upper left: model RDM coding for sensitivity to complexity processing, regardless of type. Blue indicates correlated activation patterns due to a shared property (presence of complexity), red indicates no correlation. Upper right: cartoon representation of the hypothesized distribution of the activations patterns in any given region. Each dot represents one activation pattern; the dissimilarity between them is shown as distance in 2D Euclidean space. Bottom: Brain regions that significantly correlate with this model (P < 0.05). c) A model RDM which codes for differential sensitivity to inflectional and phrasal complexity. Regions that significantly correlate with this model (P < 0.05) are shown in yellow. Red stripes indicate regions where this model fits significantly better than the general complexity model.

Figure 3

a) “Detector” models, coding for the processing of stems, inflected forms and phrases. Significant correlations for each model (P < 0.05) are shown in yellow. Red lines indicate significantly better fit of the phrase model over the inflection model. b) “Detector” models modulated by verb dominance. Red stripes denote regions of significantly better fit of inflections over phrases, and vice versa. c) Distances between regions and “detector” models in multidimensional space (MDS). Line area (length × thickness) specifies the distances, to compensate for distortions introduced by the projection from multidimensional space into 2D. Frontal regions are represented in red, temporal regions in blue; filled circles = LH, empty circles = RH