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.
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
January 2025
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
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).
.
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
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