The University of Southampton
University of Southampton Institutional Repository

Uncertainty modelling in under-represented languages with Bayesian deep Gaussian processes

Uncertainty modelling in under-represented languages with Bayesian deep Gaussian processes
Uncertainty modelling in under-represented languages with Bayesian deep Gaussian processes

NLP models often face challenges with underrepresented languages due to a lack of sufficient training data and language complexities. This can result in inaccurate predictions and a failure to capture the inherent uncertainties within these languages. This paper introduces a new method for modelling uncertainty in under-represented languages by employing deep Bayesian Gaussian Processes. We develop a novel framework that integrates prior knowledge and leverages kernel functions. This helps enable the quantification of uncertainty in predictions to overcome the data limitations in under-represented languages. The efficacy of our approach is validated through various experiments, and the results are benchmarked against existing methods to highlight the enhancements in prediction accuracy and measurement of uncertainty.

2951-2093
1438-1450
Association for Computational Linguistics (ACL)
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
50ba09b3-b2f4-4e1a-881f-ad26fbb0a1a5
Jameel, Shoaib
d79afef2-5f76-499f-9a37-a2c7550d5e41
Rambow, Owen
Wanner, Leo
Apidianaki, Marianna
Al-Khalifa, Hend
Di Eugenio, Barbara
Schockaert, Steven
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
50ba09b3-b2f4-4e1a-881f-ad26fbb0a1a5
Jameel, Shoaib
d79afef2-5f76-499f-9a37-a2c7550d5e41
Rambow, Owen
Wanner, Leo
Apidianaki, Marianna
Al-Khalifa, Hend
Di Eugenio, Barbara
Schockaert, Steven

Azam, Ubaid, Razzak, Imran, Vishwakarma, Shelly and Jameel, Shoaib (2025) Uncertainty modelling in under-represented languages with Bayesian deep Gaussian processes. Rambow, Owen, Wanner, Leo, Apidianaki, Marianna, Al-Khalifa, Hend, Di Eugenio, Barbara and Schockaert, Steven (eds.) In Proceedings - International Conference on Computational Linguistics, COLING. vol. Part F206484-1, Association for Computational Linguistics (ACL). pp. 1438-1450 .

Record type: Conference or Workshop Item (Paper)

Abstract

NLP models often face challenges with underrepresented languages due to a lack of sufficient training data and language complexities. This can result in inaccurate predictions and a failure to capture the inherent uncertainties within these languages. This paper introduces a new method for modelling uncertainty in under-represented languages by employing deep Bayesian Gaussian Processes. We develop a novel framework that integrates prior knowledge and leverages kernel functions. This helps enable the quantification of uncertainty in predictions to overcome the data limitations in under-represented languages. The efficacy of our approach is validated through various experiments, and the results are benchmarked against existing methods to highlight the enhancements in prediction accuracy and measurement of uncertainty.

Text
2025.coling-main.96 - Version of Record
Available under License Creative Commons Attribution.
Download (469kB)

More information

Published date: January 2025
Venue - Dates: 31st International Conference on Computational Linguistics, COLING 2025, , Abu Dhabi, United Arab Emirates, 2025-01-19 - 2025-01-24

Identifiers

Local EPrints ID: 503257
URI: http://eprints.soton.ac.uk/id/eprint/503257
ISSN: 2951-2093
PURE UUID: 5325e1cb-2a46-4e93-82ff-0cd5d363d8be

Catalogue record

Date deposited: 25 Jul 2025 16:38
Last modified: 21 Aug 2025 05:10

Export record

Contributors

Author: Ubaid Azam
Author: Imran Razzak
Author: Shelly Vishwakarma
Author: Shoaib Jameel
Editor: Owen Rambow
Editor: Leo Wanner
Editor: Marianna Apidianaki
Editor: Hend Al-Khalifa
Editor: Barbara Di Eugenio
Editor: Steven Schockaert

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×