Abstract:Lexical difficulty prediction is a fundamental problem in language learning and readability assessment, requiring models to estimate word difficulty across different first-language (L1) backgrounds. However, existing approaches rely on regression-only training with scalar supervision, which does not explicitly structure the representation space, limiting their ability to capture cross-lingual alignment and ordinal difficulty. To mitigate these issues, we propose Context-Aligned Contrastive Regression, which integrates Ridge regression ensemble with two complementary objectives, i.e., Cross-View Context and Ordinal Soft Contrastive Learning. Experiments on three L1 datasets show that (i) contrastive objectives improve cross-lingual representation alignment while preserving language-specific nuances, (ii) the learned representations capture the ordinal structure of lexical difficulty, and (iii) the ensemble effectively mitigates systematic biases of individual models, leading to more stable performance across difficulty levels.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08950 [cs.CL] |
| (or arXiv:2605.08950v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08950 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wicaksono Leksono [view email]
[v1]
Sat, 9 May 2026 13:43:54 UTC (3,540 KB)