Saved in:
Bibliographic Details
Main Authors: Bhandari, Diksha, Lopopolo, Alessandro, Rabovsky, Milena, Reich, Sebastian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.02590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910928192143360
author Bhandari, Diksha
Lopopolo, Alessandro
Rabovsky, Milena
Reich, Sebastian
author_facet Bhandari, Diksha
Lopopolo, Alessandro
Rabovsky, Milena
Reich, Sebastian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02590
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ensemble Kalman filter for uncertainty in human language comprehension
Bhandari, Diksha
Lopopolo, Alessandro
Rabovsky, Milena
Reich, Sebastian
Computation and Language
Applications
Machine Learning
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.
title Ensemble Kalman filter for uncertainty in human language comprehension
topic Computation and Language
Applications
Machine Learning
url https://arxiv.org/abs/2505.02590