SOTAVerified

Linguistic Acceptability

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

Image Source: Warstadt et al

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 72 papers

TitleStatusHype
LLM.int8(): 8-bit Matrix Multiplication for Transformers at ScaleCode5
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingCode3
ERNIE 2.0: A Continual Pre-training Framework for Language UnderstandingCode3
Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerCode2
Fietje: An open, efficient LLM for DutchCode2
ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsCode2
DeBERTa: Decoding-enhanced BERT with Disentangled AttentionCode2
Q8BERT: Quantized 8Bit BERTCode1
A Statistical Framework for Low-bitwidth Training of Deep Neural NetworksCode1
Big Bird: Transformers for Longer SequencesCode1
Charformer: Fast Character Transformers via Gradient-based Subword TokenizationCode1
ChatGPT: Jack of all trades, master of noneCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighterCode1
Entailment as Few-Shot LearnerCode1
FNet: Mixing Tokens with Fourier TransformsCode1
GeDi: Generative Discriminator Guided Sequence GenerationCode1
How to Train BERT with an Academic BudgetCode1
RealFormer: Transformer Likes Residual AttentionCode1
JCoLA: Japanese Corpus of Linguistic AcceptabilityCode1
Learning to Encode Position for Transformer with Continuous Dynamical ModelCode1
LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-TuningCode1
On the Robustness of Language Encoders against Grammatical ErrorsCode1
Masked Language Model ScoringCode1
RoBERTa: A Robustly Optimized BERT Pretraining ApproachCode1
RuCoLA: Russian Corpus of Linguistic AcceptabilityCode1
ScandEval: A Benchmark for Scandinavian Natural Language ProcessingCode1
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationCode1
Synthesizer: Rethinking Self-Attention in Transformer ModelsCode1
tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and EvaluationCode1
Towards Debiasing Sentence RepresentationsCode1
Linguistic Analysis of Pretrained Sentence Encoders with Acceptability Judgments—0
Grammatical Analysis of Pretrained Sentence Encoders with Acceptability Judgments—0
Grammaticality and Language Modelling—0
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding—0
How well can machine-generated texts be identified and can language models be trained to avoid identification?—0
Robust ASR Error Correction with Conservative Data Filtering—0
Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT—0
Learning Phonotactics from Linguistic Informants—0
What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning—0
Not all layers are equally as important: Every Layer Counts BERT—0
CLEAR: Contrastive Learning for Sentence Representation—0
Cross-Architecture Distillation Using Bidirectional CMOW Embeddings—0
DaLAJ - a dataset for linguistic acceptability judgments for Swedish: Format, baseline, sharing—0
DaLAJ – a dataset for linguistic acceptability judgments for Swedish—0
Data-Free Distillation of Language Model by Text-to-Text Transfer—0
Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection—0
Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective—0
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT—0
Rating Distributions and Bayesian Inference: Enhancing Cognitive Models of Spatial Language Use—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsCoLARuCoLACoLA DevItaCoLADaLAJ

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1En-BERT + TDA + PCAAccuracy88.6—Unverified
2BERT+TDAAccuracy88.2—Unverified
3RoBERTa+TDAAccuracy87.3—Unverified
4deberta-v3-base+tasksourceAccuracy87.15—Unverified
5RoBERTa-large 355M + Entailment as Few-shot LearnerAccuracy86.4—Unverified
6LTG-BERT-base 98MAccuracy82.7—Unverified
7ELC-BERT-base 98MAccuracy82.6—Unverified
8En-BERT + TDAAccuracy82.1—Unverified
9FNet-LargeAccuracy78—Unverified
10LTG-BERT-small 24MAccuracy77.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Ru-RoBERTa+TDAMCC0.59—Unverified
2ruRoBERTaMCC0.53—Unverified
3Ru-BERT+TDAMCC0.48—Unverified
4RemBERTMCC0.44—Unverified
5ruBERTMCC0.42—Unverified
6ruGPT-3MCC0.3—Unverified
7ruT5MCC0.25—Unverified
8mBERTMCC0.15—Unverified
9XLM-RMCC0.13—Unverified
#ModelMetricClaimedVerifiedStatus
1En-BERT + TDAAccuracy88.6—Unverified
2XLM-R (pre-trained) + TDAAccuracy73—Unverified
3DeBERTa (large)Accuracy69.5—Unverified
4TinyBERT-6 67MAccuracy54—Unverified
5Synthesizer (R+V)Accuracy53.3—Unverified
6En-BERT (pre-trained) + TDAMCC0.42—Unverified
#ModelMetricClaimedVerifiedStatus
1XLM-R + TDAMCC0.68—Unverified
2XLM-RMCC0.52—Unverified
3It-BERT (pre-trained) + TDAMCC0.48—Unverified
4mBERTMCC0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Sw-BERT + H0MAccuracy76.9—Unverified