Text Classification On Weebit Readability

Accuracy (5-fold)

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
BERT-FP-LBL	0.927	A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss
BART-RF-T1 hybrid	0.905	Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features
BERT	0.857	Supervised and Unsupervised Neural Approaches to Text Readability
BERT + SVM (with Handcrafted Features)	0.838	Linguistic Features for Readability Assessment
SVM (Support Vector Machine) with Handcrafted Features	0.803	Text Readability Assessment for Second Language Learners

0 of 5 row(s) selected.