Grammatical Error Correction on CoNLL-2014 Shared Task

Metric: F0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	F0.5▼	Extra Data	Paper	Date↕	Code
1	Ensembles of best 7 models + GRECO + GTP-rerank	72.8	No	Pillars of Grammatical Error Correction: Compreh...	2024-04-23	Code
2	Majority-voting ensemble on best 7 models	71.8	No	Pillars of Grammatical Error Correction: Compreh...	2024-04-23	Code
3	GRECO (voting+ESC)	71.12	No	System Combination via Quality Estimation for Gr...	2023-10-23	Code
4	GEC-DI (LM+GED)	69.6	No	Improving Seq2Seq Grammatical Error Correction v...	2023-10-23	Code
5	Unsupervised GEC + cLang8	69.6	No	-	-	Code
6	ESC	69.51	No	-	-	Code
7	T5	68.87	No	A Simple Recipe for Multilingual Grammatical Err...	2021-06-07	Code
8	MoECE	67.79	No	Efficient and Interpretable Grammatical Error Co...	2024-10-30	Code
9	SynGEC	67.6	No	SynGEC: Syntax-Enhanced Grammatical Error Correc...	2022-10-22	Code
10	Sequence tagging + token-level transformations + two-stage fine-tuning (+BERT, RoBERTa, XLNet)	66.5	No	GECToR -- Grammatical Error Correction: Tag, Not...	2020-05-26	Code
11	LM-Critic	65.8	No	LM-Critic: Language Models for Unsupervised Gram...	2021-09-14	Code
12	Sequence tagging + token-level transformations + two-stage fine-tuning (+XLNet)	65.3	No	GECToR -- Grammatical Error Correction: Tag, Not...	2020-05-26	Code
13	Transformer + Pre-train with Pseudo Data (+BERT)	65.2	No	Encoder-Decoder Models Can Benefit from Pre-trai...	2020-05-03	Code
14	Transformer + Pre-train with Pseudo Data	65	No	An Empirical Study of Incorporating Pseudo Data ...	2019-09-02	Code
15	VERNet	63.7	No	Neural Quality Estimation with Multiple Hypothes...	2021-05-10	Code
16	BART	63	No	Stronger Baselines for Grammatical Error Correct...	2020-05-24	Code
17	Sequence Labeling with edits using BERT, Faster inference	61.2	No	Parallel Iterative Edit Models for Local Sequenc...	2019-10-07	Code
18	Copy-augmented Model (4 Ensemble +Denoising Autoencoder)	61.15	No	Improving Grammatical Error Correction via Pre-T...	2019-03-01	Code
19	Sequence Labeling with edits using BERT, Faster inference (Single Model)	59.7	No	Parallel Iterative Edit Models for Local Sequenc...	2019-10-07	Code
20	CNN Seq2Seq + Quality Estimation	56.52	No	-	-	Code
21	SMT + BiGRU	56.25	No	Near Human-Level Performance in Grammatical Erro...	2018-04-16	-
22	Transformer	55.8	No	Approaching Neural Grammatical Error Correction ...	2018-04-16	Code
23	CNN Seq2Seq	54.79	No	A Multilayer Convolutional Encoder-Decoder Neura...	2018-01-26	Code

#1Ensembles of best 7 models + GRECO + GTP-rerankSOTA
72.8
F0.5· 2024-04-23
Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models Code
#2Majority-voting ensemble on best 7 models
71.8
F0.5· 2024-04-23
Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models Code
#3GRECO (voting+ESC)SOTA
71.12
F0.5· 2023-10-23
System Combination via Quality Estimation for Grammatical Error Correction Code
#4GEC-DI (LM+GED)
69.6
F0.5· 2023-10-23
Improving Seq2Seq Grammatical Error Correction via Decoding Interventions Code
#5Unsupervised GEC + cLang8
69.6
F0.5
No paperCode
#6ESC
69.51
F0.5
No paperCode
#7T5SOTA
68.87
F0.5· 2021-06-07
A Simple Recipe for Multilingual Grammatical Error Correction Code
#8MoECE
67.79
F0.5· 2024-10-30
Efficient and Interpretable Grammatical Error Correction with Mixture of Experts Code
#9SynGEC
67.6
F0.5· 2022-10-22
SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser Code
#10Sequence tagging + token-level transformations + two-stage fine-tuning (+BERT, RoBERTa, XLNet)SOTA
66.5
F0.5· 2020-05-26
GECToR -- Grammatical Error Correction: Tag, Not Rewrite Code
#11LM-Critic
65.8
F0.5· 2021-09-14
LM-Critic: Language Models for Unsupervised Grammatical Error Correction Code
#12Sequence tagging + token-level transformations + two-stage fine-tuning (+XLNet)
65.3
F0.5· 2020-05-26
GECToR -- Grammatical Error Correction: Tag, Not Rewrite Code
#13Transformer + Pre-train with Pseudo Data (+BERT)SOTA
65.2
F0.5· 2020-05-03
Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction Code
#14Transformer + Pre-train with Pseudo DataSOTA
65
F0.5· 2019-09-02
An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction Code
#15VERNet
63.7
F0.5· 2021-05-10
Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction Code
#16BART
63
F0.5· 2020-05-24
Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Model Code
#17Sequence Labeling with edits using BERT, Faster inference
61.2
F0.5· 2019-10-07
Parallel Iterative Edit Models for Local Sequence Transduction Code
#18Copy-augmented Model (4 Ensemble +Denoising Autoencoder)SOTA
61.15
F0.5· 2019-03-01
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data Code
#19Sequence Labeling with edits using BERT, Faster inference (Single Model)
59.7
F0.5· 2019-10-07
Parallel Iterative Edit Models for Local Sequence Transduction Code
#20CNN Seq2Seq + Quality Estimation
56.52
F0.5
No paperCode
#21SMT + BiGRUSOTA
56.25
F0.5· 2018-04-16
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
#22Transformer
55.8
F0.5· 2018-04-16
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task Code
#23CNN Seq2SeqSOTA
54.79
F0.5· 2018-01-26
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction Code