Work

SurreyCTS at BEA 2026 Shared Task 1: Semantic Funnelling and Entropy-based Multilingual Lexical Difficulty Prediction

Year: 2026

Type: conference-paper

Abstract: 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 baseline 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 baseline in all three settings and placing fifth among open-track teams. * Equal contribution.1 Code and configuration files are available at https:// github.com/surrey-nlp/bea2026-surrey.

Source: Workshop on Innovative Use of NLP for Building Educational Applications

DOI: 10.18653/v1/2026.bea-1.70

Authors: Georgina Willoughby, Jordan Painter, Diptesh Kanojia, Emily Wells, Constantin Orasan

Institution: University of Surrey

Language: English

Topic: Text Readability and Simplification

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Leverhulme Trust

OpenAlex ID: W7166882984