Creating a hybrid rule and neural network based semantic tagger using silver standard data: the PyMUSAS framework for multilingual semantic annotation

Moore, Andrew, Rayson, Paul, Archer, Dawn, Czerniak, Tim, Knight, Dawn ORCID: https://orcid.org/0000-0002-4745-6502, Lal, Daisy Monika, Ó Donnchadha, Gearoid, Ó Meachair, Michael J., Piao, Scott, Uí Dhonnchadha, Elaine, Vuorinen, Johanna, Yabo, Yan and Yang, Xiaobin 2026. Creating a hybrid rule and neural network based semantic tagger using silver standard data: the PyMUSAS framework for multilingual semantic annotation. Presented at: Learning Resources Evaluation Conference 2026 (LREC), Palma de Mallorca, Spain, 13-15 May 2026. Published in: Piperidis, Stelios, Bel, Nuria, van den Heuvel, Henk, Ide, Nancy, Krek, Simon and Toral, Antonio eds. Proceedings of Learning Resources Evaluation Conference 2026 (LREC). ELRA, pp. 11822-11833. 10.63317/4ngkupgnrbgc

PDF - Published Version Available under License Creative Commons Attribution Non-commercial. Download (1MB)

Abstract

Word Sense Disambiguation (WSD) has been widely evaluated using the semantic frameworks of WordNet, BabelNet, and the Oxford Dictionary of English. However, for the UCREL Semantic Analysis System (USAS) framework, no open extensive evaluation has been performed beyond lexical coverage or single language evaluation. In this work, we perform the largest semantic tagging evaluation of the rule based system that uses the lexical resources in the USAS framework covering five different languages using four existing datasets and one novel Chinese dataset. We create a new silver labelled English dataset, to overcome the lack of manually tagged training data, that we train and evaluate various mono and multilingual neural models in both mono and cross-lingual evaluation setups with comparisons to their rule based counterparts, and show how a rule based system can be enhanced with a neural network model. The resulting neural network models, including the data they were trained on, the Chinese evaluation dataset, and all of the code will be released as open resources.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > English, Communication and Philosophy
Publisher:	ELRA
ISBN:	9782493814494
ISSN:	2522-2686
Date of First Compliant Deposit:	23 June 2026
Last Modified:	23 Jun 2026 12:11
URI:	https://orca.cardiff.ac.uk/id/eprint/184892

Actions (repository staff only)

Edit Item