Papers › Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features

Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features

25 Sep 2021EMNLP 2021 11arXiv:2109.12258archive 2025-07-28

Bruce W. Lee, Yoo Sung Jang, Jason Hyung-Jong Lee

We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we explore suitable transformers and traditional ML models. Then, we extract 255 handcrafted linguistic features using self-developed extraction software. Finally, we assemble those to create several hybrid models, achieving state-of-the-art (SOTA) accuracy on popular datasets in readability assessment. The use of handcrafted features help model performance on smaller datasets. Notably, our RoBERTA-RF-T1 hybrid achieves the near-perfect classification accuracy of 99%, a 20.3% increase from the previous SOTA.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

brucewlee/lingfeat officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Text Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Classification OneStopEnglish (Readability Assessment) RoBERTa-RF-T1 hybrid Accuracy (5-fold) 0.990 #1 of 5 Archive leaderboard report
Text Classification WeeBit (Readability Assessment) BART-RF-T1 hybrid Accuracy (5-fold) 0.905 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections