MétaCan
Menu
Back to cohort

Noor at BAREC Shared Task 2025: A Hybrid Transformer-Feature Architecture for Sentence-level Readability Assessment

2025· article· W4416037651 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicText Readability and Simplification
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsReadabilityTask (project management)ArchitectureTask analysis

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.868
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0020.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.032
GPT teacher head0.304
Teacher spread0.272 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicText Readability and SimplificationFrench-language works237,207