Representations from artificial neural network (ANN) language models have been shown to predict human brain activity in the language network. To understand what aspects of linguistic stimuli contribute to ANN-to-brain similarity, we used an fMRI data set of responses to n = 627 naturalistic English sentences (Pereira et al., 2018) and systematically manipulated the stimuli for which ANN representations were extracted. In particular, we (i) perturbed sentences’ word order, (ii) removed different subsets of words, or (iii) replaced sentences with other sentences of varying semantic similarity. We found that the lexical-semantic content of the sentence (largely carried by content words) rather than the sentence’s syntactic form (conveyed via word order or function words) is primarily responsible for the ANN-to-brain similarity. In follow-up analyses, we found that perturbation manipulations that adversely affect brain predictivity also lead to more divergent representations in the ANN’s embedding space and decrease the ANN’s ability to predict upcoming tokens in those stimuli. Further, results are robust as to whether the mapping model is trained on intact or perturbed stimuli and whether the ANN sentence representations are conditioned on the same linguistic context that humans saw. The critical result—that lexical-semantic content is the main contributor to the similarity between ANN representations and neural ones—aligns with the idea that the goal of the human language system is to extract meaning from linguistic strings. Finally, this work highlights the strength of systematic experimental manipulations for evaluating how close we are to accurate and generalizable models of the human language network.
The meaning of words in natural language depends crucially on context. However, most neuroimaging studies of word meaning use isolated words and isolated sentences with little context. Because the brain may process natural language differently from how it processes simplified stimuli, there is a pressing need to determine whether prior results on word meaning generalize to natural language. fMRI was used to record human brain activity while four subjects (two female) read words in four conditions that vary in context: narratives, isolated sentences, blocks of semantically similar words, and isolated words. We then compared the signal-to-noise ratio (SNR) of evoked brain responses, and we used a voxelwise encoding modeling approach to compare the representation of semantic information across the four conditions. We find four consistent effects of varying context. First, stimuli with more context evoke brain responses with higher SNR across bilateral visual, temporal, parietal, and prefrontal cortices compared with stimuli with little context. Second, increasing context increases the representation of semantic information across bilateral temporal, parietal, and prefrontal cortices at the group level. In individual subjects, only natural language stimuli consistently evoke widespread representation of semantic information. Third, context affects voxel semantic tuning. Finally, models estimated using stimuli with little context do not generalize well to natural language. These results show that context has large effects on the quality of neuroimaging data and on the representation of meaning in the brain. Thus, neuroimaging studies that use stimuli with little context may not generalize well to the natural regime.
- NSF-PAR ID:
- 10409229
- Publisher / Repository:
- DOI PREFIX: 10.1523
- Date Published:
- Journal Name:
- The Journal of Neuroscience
- Volume:
- 43
- Issue:
- 17
- ISSN:
- 0270-6474
- Page Range / eLocation ID:
- p. 3144-3158
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Neuroimaging studies of human memory have consistently found that univariate responses in parietal cortex track episodic experience with stimuli (whether stimuli are 'old' or 'new'). More recently, pattern-based fMRI studies have shown that parietal cortex also carries information about the semantic content of remembered experiences. However, it is not well understood how memory-based and content-based signals are integrated within parietal cortex. Here, in humans (males and females), we used voxel-wise encoding models and a recognition memory task to predict the fMRI activity patterns evoked by complex natural scene images based on (1) the episodic history and (2) the semantic content of each image. Models were generated and compared across distinct subregions of parietal cortex and for occipitotemporal cortex. We show that parietal and occipitotemporal regions each encode memory and content information, but they differ in how they combine this information. Among parietal subregions, angular gyrus was characterized by robust and overlapping effects of memory and content. Moreover, subject-specific semantic tuning functions revealed that successful recognition shifted the amplitude of tuning functions in angular gyrus but did not change the selectivity of tuning. In other words, effects of memory and content were additive in angular gyrus. This pattern of data contrasted with occipitotemporal cortex where memory and content effects were interactive: memory effects were preferentially expressed by voxels tuned to the content of a remembered image. Collectively, these findings provide unique insight into how parietal cortex combines information about episodic memory and semantic content.
SIGNIFICANCE STATEMENT Neuroimaging studies of human memory have identified multiple brain regions that not only carry information about “whether” a visual stimulus is successfully recognized but also “what” the content of that stimulus includes. However, a fundamental and open question concerns how the brain integrates these two types of information (memory and content). Here, using a powerful combination of fMRI analysis methods, we show that parietal cortex, particularly the angular gyrus, robustly combines memory- and content-related information, but these two forms of information are represented via additive, independent signals. In contrast, memory effects in high-level visual cortex critically depend on (and interact with) content representations. Together, these findings reveal multiple and distinct ways in which the brain combines memory- and content-related information. -
Because meaning can often be inferred from lexical semantics alone, word order is often a redundant cue in natural language. For example, the words chopped, chef, and onion are more likely used to convey “The chef chopped the onion,” not “The onion chopped the chef.” Recent work has shown large language models to be surprisingly word order invariant, but crucially has largely considered natural prototypical inputs, where compositional meaning mostly matches lexical expectations. To overcome this confound, we probe grammatical role representation in English BERT and GPT-2, on instances where lexical expectations are not sufficient, and word order knowledge is necessary for correct classification. Such non-prototypical instances are naturally occurring English sentences with inanimate subjects or animate objects, or sentences where we systematically swap the arguments to make sentences like “The onion chopped the chef”. We find that, while early layer embeddings are largely lexical, word order is in fact crucial in defining the later-layer representations of words in semantically non-prototypical positions. Our experiments isolate the effect of word order on the contextualization process, and highlight how models use context in the uncommon, but critical, instances where it matters.more » « less
-
more » « less
Abstract Reading entails transforming visual symbols to sound and meaning. This process depends on specialized circuitry in the visual cortex, the visual word form area (VWFA). Recent findings suggest that this text‐selective cortex comprises at least two distinct subregions: the more posterior VWFA‐1 is sensitive to visual features, while the more anterior VWFA‐2 processes higher level language information. Here, we explore whether these two subregions also exhibit different patterns of functional connectivity. To this end, we capitalize on two complementary datasets: Using the Natural Scenes Dataset (NSD), we identify text‐selective responses in high‐quality 7T adult data (
N = 8), and investigate functional connectivity patterns of VWFA‐1 and VWFA‐2 at the individual level. We then turn to the Healthy Brain Network (HBN) database to assess whether these patterns replicate in a large developmental sample (N = 224; age 6–20 years), and whether they relate to reading development. In both datasets, we find that VWFA‐1 is primarily correlated with bilateral visual regions. In contrast, VWFA‐2 is more strongly correlated with language regions in the frontal and lateral parietal lobes, particularly the bilateral inferior frontal gyrus. Critically, these patterns do not generalize to adjacent face‐selective regions, suggesting a specific relationship between VWFA‐2 and the frontal language network. No correlations were observed between functional connectivity and reading ability. Together, our findings support the distinction between subregions of the VWFA, and suggest that functional connectivity patterns in the ventral temporal cortex are consistent over a wide range of reading skills. -
more » « less
Abstract During language processing, people make rapid use of contextual information to promote comprehension of upcoming words. When new words are learned implicitly, information contained in the surrounding context can provide constraints on their possible meaning. In the current study, EEG was recorded as participants listened to a series of three sentences, each containing an identical target pseudoword, with the aim of using contextual information in the surrounding language to identify a meaning representation for the novel word. In half of the trials, sentences were semantically coherent so that participants could develop a single representation for the novel word that fit all contexts. Other trials contained unrelated sentence contexts so that meaning associations were not possible. We observed greater theta band enhancement over the left hemisphere across central and posterior electrodes in response to pseudowords processed across semantically related compared to unrelated contexts. Additionally, relative alpha and beta band suppression was increased prior to pseudoword onset in trials where contextual information more readily promoted pseudoword meaning associations. Under the hypothesis that theta enhancement indexes processing demands during lexical access, the current study provides evidence for selective online memory retrieval for novel words learned implicitly in a spoken context.
