Linguistic Acceptability On Cola

평가 지표

Accuracy

MCC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	MCC	Paper Title	Repository
BERT+TDA	88.2%	0.726	Can BERT eat RuCoLA? Topological Data Analysis to Explain
RoBERTa (ensemble)	67.8%	-	RoBERTa: A Robustly Optimized BERT Pretraining Approach
T5-Base	51.1%	-	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
LTG-BERT-base 98M	82.7	-	Not all layers are equally as important: Every Layer Counts BERT	-
En-BERT + TDA	82.1%	0.565	Acceptability Judgements via Examining the Topology of Attention Maps
RemBERT	-	0.6	RuCoLA: Russian Corpus of Linguistic Acceptability
24hBERT	57.1	-	How to Train BERT with an Academic Budget
MLM+ del-span+ reorder	64.3%	-	CLEAR: Contrastive Learning for Sentence Representation	-
ELECTRA	68.2%	-	-	-
ERNIE 2.0 Large	63.5%	-	ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
deberta-v3-base+tasksource	87.15%	-	tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation
SqueezeBERT	46.5%	-	SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
T5-XL 3B	67.1%	-	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
FLOATER-large	69%	-	Learning to Encode Position for Transformer with Continuous Dynamical Model
LM-CPPF RoBERTa-base	14.1%	-	LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
StructBERTRoBERTa ensemble	69.2%	-	StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding	-
data2vec	60.3%	-	data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
ERNIE	52.3%	-	ERNIE: Enhanced Language Representation with Informative Entities
Q8BERT (Zafrir et al., 2019)	65.0	-	Q8BERT: Quantized 8Bit BERT
T5-Small	41.0%	-	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

0 of 43 row(s) selected.