Ensemble Kalman filter for uncertainty in human language comprehension
This addresses the limitation of traditional models in reflecting human cognitive processing of linguistic ambiguities, though it is incremental as it builds on existing models like the Sentence Gestalt model.
The paper tackled the problem of deterministic behavior in artificial neural networks modeling sentence processing by proposing a Bayesian framework using an ensemble Kalman filter to quantify uncertainty, demonstrating improved uncertainty representation compared to maximum likelihood estimation.
Artificial neural networks (ANNs) are widely used in modeling sentence processing but often exhibit deterministic behavior, contrasting with human sentence comprehension, which manages uncertainty during ambiguous or unexpected inputs. This is exemplified by reversal anomalies-sentences with unexpected role reversals that challenge syntax and semantics-highlighting the limitations of traditional ANN models, such as the Sentence Gestalt (SG) Model. To address these limitations, we propose a Bayesian framework for sentence comprehension, applying an extension of the ensemble Kalman filter (EnKF) for Bayesian inference to quantify uncertainty. By framing language comprehension as a Bayesian inverse problem, this approach enhances the SG model's ability to reflect human sentence processing with respect to the representation of uncertainty. Numerical experiments and comparisons with maximum likelihood estimation (MLE) demonstrate that Bayesian methods improve uncertainty representation, enabling the model to better approximate human cognitive processing when dealing with linguistic ambiguities.