A fundamental question in neurolinguistics concerns the brain regions involved in syntactic and semantic processing during speech comprehension, both at the lexical (word processing) and supra-lexical levels (sentence and discourse processing). To what extent are these regions separated or intertwined? To address this question, we introduce a novel approach exploiting neural language models to generate high-dimensional feature sets that separately encode semantic and syntactic information. More precisely, we train a lexical language model, GloVe, and a supra-lexical language model, GPT-2, on a text corpus from which we selectively removed either syntactic or semantic information. We then assess to what extent the features derived from these information-restricted models are still able to predict the fMRI time courses of humans listening to naturalistic text. Furthermore, to determine the windows of integration of brain regions involved in supra-lexical processing, we manipulate the size of contextual information provided to GPT-2. The analyses show that, while most brain regions involved in language comprehension are sensitive to both syntactic and semantic features, the relative magnitudes of these effects vary across these regions. Moreover, regions that are best fitted by semantic or syntactic features are more spatially dissociated in the left hemisphere than in the right one, and the right hemisphere shows sensitivity to longer contexts than the left. The novelty of our approach lies in the ability to control for the information encoded in the models’ embeddings by manipulating the training set. These “information-restricted” models complement previous studies that used language models to probe the neural bases of language, and shed new light on its spatial organization.
Children show a remarkable degree of consistency in learning some words earlier than others. What patterns of word usage predict variations among words in age of acquisition? We use distributional analysis of a naturalistic corpus of child‐directed speech to create quantitative features representing natural variability in word contexts. We evaluate two sets of features: One set is generated from the distribution of words into frames defined by the two adjacent words. These features primarily encode syntactic aspects of word usage. The other set is generated from non‐adjacent co‐occurrences between words. These features encode complementary thematic aspects of word usage. Regression models using these distributional features to predict age of acquisition of 656 early‐acquired English words indicate that both types of features improve predictions over simpler models based on frequency and appearance in salient or simple utterance contexts. Syntactic features were stronger predictors of children's production than comprehension, whereas thematic features were stronger predictors of comprehension. Overall, earlier acquisition was predicted by features representing frames that select for nouns and verbs, and by thematic content related to food and face‐to‐face play topics; later acquisition was predicted by features representing frames that select for pronouns and question words, and by content related to narratives and object play.
more » « less- NSF-PAR ID:
- 10244982
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Cognitive Science
- Volume:
- 44
- Issue:
- 11
- ISSN:
- 0364-0213
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Abstract What makes a word easy to learn? Early‐learned words are frequent and tend to name concrete referents. But words typically do not occur in isolation. Some words are predictable from their contexts; others are less so. Here, we investigate whether predictability relates to when children start producing different words (age of acquisition; AoA). We operationalized predictability in terms of a word's surprisal in child‐directed speech, computed using n‐gram and long‐short‐term‐memory (LSTM) language models. Predictability derived from LSTMs was generally a better predictor than predictability derived from n‐gram models. Across five languages, average surprisal was positively correlated with the AoA of predicates and function words but not nouns. Controlling for concreteness and word frequency, more predictable predicates and function words were learned earlier. Differences in predictability between languages were associated with cross‐linguistic differences in AoA: the same word (when it was a predicate) was produced earlier in languages where the word was more predictable.
-
more » « less
Abstract Children use syntax to learn verbs, in a process known as syntactic bootstrapping. The structure‐mapping account proposes that syntactic bootstrapping begins with a universal bias to map each noun phrase in a sentence onto a participant role in a structured conceptual representation of an event. Equipped with this bias, children interpret the
number of noun phrases accompanying a new verb as evidence about the semantic predicate–argument structure of the sentence, and therefore about the meaning of the verb. In this paper, we first review evidence for the structure–mapping account, and then discuss challenges to the account arising from the existence of languages that allow verbs' arguments to be omitted, such as Korean. These challenges prompt us to (a) refine our notion of the distributional learning mechanisms that create representations of sentence structure, and (b) propose that anexpectation of discourse continuity allows children to gather linguistic evidence for each verb’s arguments across sentences in a coherent discourse. Taken together, the proposed learning mechanisms and biases sketch a route whereby simple aspects of sentence structure guide verb learning from the start of multi‐word sentence comprehension, and do so even if some of the new verb’s arguments are omitted due to discourse redundancy. -
more » « less
Abstract Capturing evidence for dynamic changes in self‐regulated learning (SRL) behaviours resulting from interventions is challenging for researchers. In the current study, we identified students who were likely to do poorly in a biology course and those who were likely to do well. Then, we randomly assigned a portion of the students predicted to perform poorly to a science of learning to learn intervention where they were taught SRL study strategies. Learning outcome and log data (257 K events) were collected from
n = 226 students. We used a complex systems framework to model the differences in SRL including the amount, interrelatedness, density and regularity of engagement captured in digital trace data (ie, logs). Differences were compared between students who were predicted to (1) perform poorly (control,n = 48), (2) perform poorly and received intervention (treatment,n = 95) and (3) perform well (not flagged,n = 83). Results indicated that the regularity of students' engagement was predictive of course grade, and that the intervention group exhibited increased regularity in engagement over the control group immediately after the intervention and maintained that increase over the course of the semester. We discuss the implications of these findings in relation to the future of artificial intelligence and potential uses for monitoring student learning in online environments.Practitioner notes What is already known about this topic
Self‐regulated learning (SRL) knowledge and skills are strong predictors of postsecondary STEM student success.
SRL is a dynamic, temporal process that leads to purposeful student engagement.
Methods and metrics for measuring dynamic SRL behaviours in learning contexts are needed.
What this paper adds
A Markov process for measuring dynamic SRL processes using log data.
Evidence that dynamic, interaction‐dominant aspects of SRL predict student achievement.
Evidence that SRL processes can be meaningfully impacted through educational intervention.
Implications for theory and practice
Complexity approaches inform theory and measurement of dynamic SRL processes.
Static representations of dynamic SRL processes are promising learning analytics metrics.
Engineered features of LMS usage are valuable contributions to AI models.
-
more » « less
Abstract Mandarin requires neither determiners nor morphological inflections, which casts doubt on Mandarin‐speaking children's ability to use function words as a syntactic bootstrapping tool to identify the form class of a new word. This study examined 3‐ and 5‐year‐old Mandarin learners' ability to use function words to interpret new words as either nouns or verbs in the absence of the requirement for determiners and inflections in the ambient language. In Experiment 1, 3‐, and 5‐year‐old Mandarin‐speaking children were exposed to eight novel words embedded in sentence frames differing only in the form class markers used. The 5‐year‐olds interpreted the novel words as either nouns or verbs depending on the form class markers they heard, while the 3‐year‐olds learned only the nouns. Experiment 2 confirmed that the 5‐year‐olds understood the function of the verb‐marker. Thus, Mandarin‐speaking children can use function words to distinguish nouns versus verbs, and this ability appears between three and five years of age.
