SOTAVerified|Agents Browse Leaderboard About

Linguistic Acceptability

Linguistic Acceptability is the task of determining whether a sentence is grammatical or ungrammatical.

Image Source: Warstadt et al

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 31–40 of 72 papers

Title	Date	Tasks	Status	Hype
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization	Jun 23, 2021	Inductive BiasLinguistic Acceptability	CodeCode Available	1
Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT	Jun 1, 2021	CoLADecision Making	—Unverified	0
Language Models Use Monotonicity to Assess NPI Licensing	May 28, 2021	DiagnosticLinguistic Acceptability	CodeCode Available	0
DaLAJ - a dataset for linguistic acceptability judgments for Swedish: Format, baseline, sharing	May 14, 2021	Binary ClassificationLinguistic Acceptability	—Unverified	0
FNet: Mixing Tokens with Fourier Transforms	May 9, 2021	Linguistic AcceptabilityMachine Translation	CodeCode Available	1
DaLAJ – a dataset for linguistic acceptability judgments for Swedish	May 1, 2021	Linguistic Acceptability	—Unverified	0
Entailment as Few-Shot Learner	Apr 29, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
How to Train BERT with an Academic Budget	Apr 15, 2021	Language ModelingLanguage Modelling	CodeCode Available	1
CLEAR: Contrastive Learning for Sentence Representation	Dec 31, 2020	Contrastive LearningLinguistic Acceptability	—Unverified	0
RealFormer: Transformer Likes Residual Attention	Dec 21, 2020	Language ModelingLanguage Modelling	CodeCode Available	1

Show:10 25 50

← PrevPage 4 of 8Next →

All datasets CoLA RuCoLA CoLA Dev ItaCoLA DaLAJ

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	En-BERT + TDA + PCA	Accuracy	88.6	—	Unverified
2	BERT+TDA	Accuracy	88.2	—	Unverified
3	RoBERTa+TDA	Accuracy	87.3	—	Unverified
4	deberta-v3-base+tasksource	Accuracy	87.15	—	Unverified
5	RoBERTa-large 355M + Entailment as Few-shot Learner	Accuracy	86.4	—	Unverified
6	LTG-BERT-base 98M	Accuracy	82.7	—	Unverified
7	ELC-BERT-base 98M	Accuracy	82.6	—	Unverified
8	En-BERT + TDA	Accuracy	82.1	—	Unverified
9	FNet-Large	Accuracy	78	—	Unverified
10	LTG-BERT-small 24M	Accuracy	77.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ru-RoBERTa+TDA	MCC	0.59	—	Unverified
2	ruRoBERTa	MCC	0.53	—	Unverified
3	Ru-BERT+TDA	MCC	0.48	—	Unverified
4	RemBERT	MCC	0.44	—	Unverified
5	ruBERT	MCC	0.42	—	Unverified
6	ruGPT-3	MCC	0.3	—	Unverified
7	ruT5	MCC	0.25	—	Unverified
8	mBERT	MCC	0.15	—	Unverified
9	XLM-R	MCC	0.13	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	En-BERT + TDA	Accuracy	88.6	—	Unverified
2	XLM-R (pre-trained) + TDA	Accuracy	73	—	Unverified
3	DeBERTa (large)	Accuracy	69.5	—	Unverified
4	TinyBERT-6 67M	Accuracy	54	—	Unverified
5	Synthesizer (R+V)	Accuracy	53.3	—	Unverified
6	En-BERT (pre-trained) + TDA	MCC	0.42	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	XLM-R + TDA	MCC	0.68	—	Unverified
2	XLM-R	MCC	0.52	—	Unverified
3	It-BERT (pre-trained) + TDA	MCC	0.48	—	Unverified
4	mBERT	MCC	0.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Sw-BERT + H0M	Accuracy	76.9	—	Unverified