Noor at BAREC Shared Task 2025: A Hybrid Transformer-Feature Architecture for Sentence-level Readability Assessment
Bibliographic record
Abstract
This paper presents my participation in the Sentence-level Readability Assessment, Strict track of the BAREC Shared Task 2025 (Elmadani et al., 2025a).Building upon prior work that fine-tuned pre-trained transformer models (Elmadani et al., 2025b), this work explores the impact of incorporating a rich set of handcrafted features on readability prediction performance.A total of 51 features were extracted from the BAREC corpus (Elmadani et al., 2025b), including morphological, lexical, and syntactic indicators, leveraging established computational linguistics tools.These features were integrated into a hybrid architecture that combines transformerbased contextual embeddings with dense layers for feature processing.To optimize performance, experiments included freezing strategies and gradual unfreezing, alongside architectural variations with additional classification layers.Among the tested models, the best performance was achieved with MARBERT, reaching a Quadratic Weighted Kappa (QWK) of 80.95% on the test set, and 83.1% on the blind test set.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.011 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".