Work

BAKER: Bayesian Kernel Uncertainty in Domain-Specific Document Modelling

Year: 2025

Type: conference-paper

Abstract: In critical domains such as healthcare and law, accurately modelling the uncertainty of automatic computational models is essential. For instance, healthcare models must produce reliable estimates to guide human decision-making. However, modelling uncertainty remains challenging, particularly for models handling low-resource datasets and complex, domain-specific vocabulary. Most existing predictive models model point estimates rather than probability distributions, limiting our ability to quantify model uncertainty. This paper introduces a novel model, BAKER, designed to address these limitations. BAKER combines the strengths of Bayesian inference, known for its effectiveness in modelling uncertainty, and kernel methods, which excel at capturing complex data relationships. Incorporating kernel functions enhances model performance, particularly by reducing overfitting in data-limited scenarios. Our experimental analysis shows that BAKER significantly improves uncertainty reasoning compared to existing models.

DOI: 10.1145/3701551.3703517

Authors: Ubaid Azam, Imran Razzak, Shelly Vishwakarma, Hakim Hacid, Dell Zhang, Shoaib Jameel

Institutions: University of Southampton, UNSW Sydney, Mohamed bin Zayed University of Artificial Intelligence, Technology Innovation Institute, China Telecom

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: Universitas Brawijaya

Award: G7851451575

OpenAlex ID: W4407953207

FWCI:

Cites: 41

Cited by:

Related to: 10