This paper describes the SurreyCTS submission 1 to the BEA 2026 shared task on lexical difficulty prediction, entered in the Open Track. Our approach progressed from base-line multilingual encoders to a hybrid Rem-BERT architecture with extensive feature engineering , combining semantic funnelling, lexical similarity features, attention-derived signals , and language-aware representations. On our internal production validation set, the best single models achieved RMSE 0.8122 (prod-H) and Pearson correlation 0.8968 (prod-G). A weighted ensemble of the five strongest systems, with weights proportional to inverse squared validation RMSE, was submitted as our final entry. On the official shared-task test set, the ensemble achieved RMSE 1.034, 0.945, and 0.861 for Spanish, German, and Chinese respectively, outperforming the open-track base-line in all three settings and placing fifth among open-track teams.
- SurreyCTS at BEA 2026 Shared Task 1: Semantic Funnelling and Entropy-based Multilingual Lexical Difficulty Prediction
- Georgina Jennifer Willoughby (Author) - University of Surrey, Literature and LanguagesJordan Mark Andrew Robert Painter (Author) - University of Surrey, Literature and LanguagesDiptesh Kanojia (Author) - University of Surrey, School of Computer Science & Electronic EngineeringEmily Frances Wells (Author) - University of Surrey, Literature and LanguagesConstantin Orasan (Author) - University of Surrey, Literature and Languages
- Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026), pp.1016-1023
- The 64th Annual Meeting of the Association for Computational Linguistics (San Diego, California, USA, 03/07/2026–04/07/2026)
- 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026), 21 (San Diego, California, United States)
- Association for Computational Linguistics
- 8
- 07/2026
- Leverhulme Trust (United Kingdom, London)
- Part of this research was supported by the Leverhulme Doctoral Scholarships Network for AI-Enabled Digital Accessibility (ADA), whose support is gratefully acknowledged.
- 991146695902346
- © 2026 Association for Computational Linguistics. ACL materials are Copyright © 1963–2026 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
- Literature and Languages
- English
- Conference proceeding