Papers by Cory Shain
BabyLM’s First Constructions: Causal interventions provide a signal of learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows sensitivity to constructions in pretrained language models, but their relevance to human language learning is doubted. |
| Approach: | They use construction grammars to demonstrate sensitivity to constructions in pretrained language models. |
| Outcome: | The proposed models learn diverse constructions even hard cases that are superficially indistinguishable. |
Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects (D18-1)
Copied to clipboard
| Challenge: | a confound exists in time series data that violates assumptions of linear models . time series may violate assumptions through temporal diffusion . |
| Approach: | They propose a statistical model that borrows from digital signal processing to fit latent impulse response functions of arbitrary shape. |
| Outcome: | The proposed model recovers true latent IRFs and improves prediction quality . it is based on a new technique that borrows from digital signal processing . |
SentSpace: Large-Scale Benchmarking and Evaluation of Text using Cognitively Motivated Lexical, Syntactic, and Semantic Features (2022.naacl-demo)
Copied to clipboard
| Challenge: | SentSpace provides a framework for streamlined evaluation of textual input. |
| Approach: | They describe the design of SentSpace and demonstrate an example use case . they use a web interface for interactive visualization and comparison with large corpora . |
| Outcome: | The framework provides a common framework for evaluation and visualization. |
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (N19-1)
Copied to clipboard
| Challenge: | Xitsonga and English are typologically unrelated languages . phonological features are not directly observed by humans . |
| Approach: | They deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages. |
| Outcome: | The proposed model is well represented in both languages, while others are less so. |
A large-scale study of the effects of word frequency and predictability in naturalistic reading (N19-1)
Copied to clipboard
| Challenge: | Recent studies have shown separable effects of word frequency and predictability on human sentence processing . other theories hold that apparent effects of frequency are underlyingly effects of predictability . |
| Approach: | They examine the generalizability of this finding to more realistic conditions of sentence processing by studying effects of frequency and predictability in three large-scale naturalistic reading corpora. |
| Outcome: | The results show that word frequency and predictability are significant in isolation but not over and above predictability, and raise doubts about the existence of such a distinction in everyday sentence comprehension. |
Constructions are Revealed in Word Distributions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Construction grammar posits that constructions are form-meaning pairings that are acquired through experience with language. |
| Approach: | They propose to use a RoBERTa model to model constructions as patterns of statistical affinity . they show that statistical affinity is likely an important, but partial, signal available to learners . |
| Outcome: | The proposed model shows that constructions will be revealed as patterns of statistical affinity . the proposed model is based on a model that is able to distinguish constructions from text . |
Coreference information guides human expectations during natural reading (2020.coling-main)
Copied to clipboard
| Challenge: | Existing theories of coreference processing focus on memory, but some theories focus on expectations. |
| Approach: | They hypothesize that coreference tracking also informs human expectations about upcoming words. |
| Outcome: | The proposed coreference-aware parser improves human response times in a naturalistic reading experiment. |
CDRNN: Discovering Complex Dynamics in Human Language Processing (2021.acl-long)
Copied to clipboard
| Challenge: | Behavioral and fMRI experiments reveal detailed and plausible estimates of human language processing dynamics . central questions in psycholinguistics concern the mental processes involved in incremental human language understanding . |
| Approach: | They propose a continuous-time deconvolutional regressive neural network that captures time-varying, non-linear, and delayed influences of predictors on the response. |
| Outcome: | The proposed neural network captures time-varying, non-linear, and delayed influences on the response . Behavioral and fMRI experiments show it generalizes better than baselines . |