The primacy of experience in language processing: Semantic priming is driven primarily by experiential similarity

Abstract

The organization of semantic memory, including memory for word meanings, has long been a central question in cognitive science. Although there is general agreement that word meaning representations must make contact with sensory-motor and affective experiences in a non-arbitrary fashion, the nature of this relationship remains controversial. One prominent view proposes that word meanings are represented directly in terms of their experiential content (i.e., sensory-motor and affective representations). Opponents of this view argue that the representation of word meanings reflects primarily taxonomic structure, that is, their relationships to natural categories. In addition, the recent success of language models based on word co-occurrence (i.e., distributional) information in emulating human linguistic behavior has led to proposals that this kind of information may play an important role in the representation of lexical concepts. We used a semantic priming paradigm designed for representational similarity analysis (RSA) to quantitatively assess how well each of these theories explains the representational similarity pattern for a large set of words. Crucially, we used partial correlation RSA to account for intercorrelations between model predictions, which allowed us to assess, for the first time, the unique effect of each model. Semantic priming was driven primarily by experiential similarity between prime and target, with no evidence of an independent effect of distributional or taxonomic similarity. Furthermore, only the experiential models accounted for unique variance in priming after partialling out explicit similarity ratings. These results support experiential accounts of semantic representation and indicate that, despite their good performance at some linguistic tasks, the distributional models evaluated here do not encode the same kind of information used by the human semantic system.

Keywords: Concept representation; Distributional semantics; Lexical decision; Lexical semantics; Semantic memory.

Figure 1.

Schematic illustration of the RSA approach. Left: priming predictions were derived from each model of word semantics (only the similarity matrix and predictions from Exp48 are shown). Right: lexical decision was performed on the same set of targets in two testing sessions, yielding a priming value for each target for each participant. Model predictions were evaluated through Spearman correlations with the observed priming.

Figure 2.

RSA correlations for experiential (light blue), distributional (red), and taxonomic (purple) models of semantic representation, for explicit ratings of semantic similarity and thematic association (orange), and for a control model based on a set of feature ratings that does not reflect the functional organization of the brain (dark blue). Horizontal lines indicate significant differences between correlations, FDR-corrected p < .05. *** FDR-corrected p < .0001.

Figure 3.

Pairwise partial correlations evaluating the unique variance explained by the experiential models (blue) while controlling for each of the other models, and the unique variance explained by the distributional (red) and taxonomic (purple) models while controlling for each experiential model. ***FDR-corrected p < .0005; **FDR-corrected p < .005; *FDR-corrected p < .01.

Figure 4.

Pairwise partial correlations evaluating the unique variance explained by the Control12 model (dark blue) while controlling for the variance explained by each of the 10 semantic models evaluated, and vice versa. ***FDR-corrected p < .0005; **FDR-corrected p < .005; *FDR-corrected p < .05.

Figure 5.

RSA results including only the 97 trials for which SFPN scores are available. Horizontal lines indicate significant differences between RSA correlations, FDR-corrected p < .05. *** FDR-corrected p < .0005, ** FDR-corrected p < .005.

Figure 6.

Pairwise partial correlations evaluating the unique variance explained by the SFPN model (green) while controlling for predictions of each of the other models, and the unique variance explained by the other models while controlling for the SFPN predictions. ***FDR-corrected p < .0005; **FDR-corrected p < .005; *FDR-corrected p < .05 (includes only the 97 trials for which SFPN scores are available).