Our new X account is live! Follow @wizwand_team for updates

Grammatical Error Correction on CoNLL 2014 (test)

72.2F0.5 Score

AGGR-RANK*

Updated 3d ago

Evaluation Results

Method
AGGR-RANK* 2024.04	72.2	81.9	49	-	-	-	-	-	-	-
AGGR-RANK 2024.04	71.8	84	45.4	-	-	-	-	-	-	-
GRECO_voting 2023.10	71.12	79.6	49.86	-	-	-	-	-	-	-
GRECO voting 2023.10	70.48	79.36	48.69	-	-	-	-	-	-	-
GRECO voting+ESC 2023.10	70.48	79.36	48.69	-	-	-	-	-	-	-
GRECO 2023.10	69.86	76.68	51.54	-	-	-	-	-	-	-
BART Baseline + CDA w/ denoising 2024.06	69.8	76.2	52.2	-	-	-	-	-	-	-
ESC 2023.10	69.51	81.48	43.78	-	-	-	-	-	-	-
GRECO 2023.10	69.23	76.39	50.35	-	-	-	-	-	-	-
Rothe et al. (2021) 2022.03	68.9	-	-	-	-	-	-	-	-	-
Rothe et al. (2021) 2022.04	68.9	-	-	-	-	-	-	-	-	-
T5-XXL 2024.06	68.9	-	-	-	-	-	-	-	-	-
MultiTaskBART 2024.06	68.9	75.4	51.2	-	-	-	-	-	-	-
BART Baseline 2024.06	68.6	73.8	53.5	-	-	-	-	-	-	-
T5-XL 2023.10	68.5	74.4	52.02	-	-	-	-	-	-	-
MEMT 2023.10	68.37	76.44	48.06	-	-	-	-	-	-	-
Stahlberg and Kumar (2021) 2022.03	68.3	75.6	49.3	-	-	-	-	-	-	-
EditScorer 2023.10	68.25	74.32	51.44	-	-	-	-	-	-	-
C4-200M 2023.10	68.13	75.47	49.06	-	-	-	-	-	-	-
TemplateGEC 2024.05	68.1	74.8	50	-	-	-	-	-	-	-
TemplateGEC 2024.06	68.1	74.8	50	-	-	-	-	-	-	-
DeCoGLM 2024.05	68	75.1	49.4	-	-	-	-	-	-	-
Kiyono et al. (2019) 2023.07	67.9	67.3	44	-	-	-	-	-	-	-
Chat-LLaMa-2-13B 2024.04	67.9	77.3	45.6	-	-	-	-	-	-	-
DeGLM-CoGLM 2024.05	67.8	75.1	49	-	-	-	-	-	-	-
T5-XL 2024.06	67.8	-	-	-	-	-	-	-	-	-
SynGEC 2022.10	67.6	74.7	49	-	-	-	-	-	-	-
SynGEC 2024.05	67.6	74.7	49	-	-	-	-	-	-	-
SynGEC 2024.06	67.6	74.7	49	-	-	-	-	-	-	-
T5-11B 2024.04	67.5	70.9	56.5	-	-	-	-	-	-	-
UL2-20B 2024.04	67.5	73.8	50.4	-	-	-	-	-	-	-
MixEdit 2024.06	67.3	75.6	46.8	-	-	-	-	-	-	-
Chat-LLaMa-2-7B 2024.04	67.2	75.5	46.8	-	-	-	-	-	-	-
BART Baseline + CDA w/o denoising 2024.06	67.1	76.7	44.8	-	-	-	-	-	-	-
GOPar 2022.10	67	74.1	48.3	-	-	-	-	-	-	-
Lichtarge et al. (2020) 2022.04	66.8	-	-	-	-	-	-	-	-	-
Our Baseline 2022.10	66.7	73.6	48.6	-	-	-	-	-	-	-
BART 2024.05	66.7	73.6	48.6	-	-	-	-	-	-	-
Stahlberg and Kumar (2021) 2022.03	66.6	72.8	49.5	-	-	-	-	-	-	-
Stahlberg and Kumar (2021) 2022.10	66.6	72.8	49.5	-	-	-	-	-	-	-
GECTOR 2020.05	66.5	78.2	41.5	-	-	-	-	-	-	-
Omelianchuk et al. (2020) 2022.03	66.5	78.2	41.5	-	-	-	-	-	-	-
Omelianchuk et al. (2020) 2023.07	66.5	78.2	41.5	-	-	-	-	-	-	-
Our approach (12+2 BART-Init) 2021.06	66.4	71	52.8	-	-	-	-	-	-	9.6
Sun et al. (2021) 2022.10	66.4	71	52.8	-	-	-	-	-	-	-
ShallowAD 2024.06	66.4	71	52.8	-	-	-	-	-	-	-
Rothe et al. (2021) 2022.10	66.1	-	-	-	-	-	-	-	-	-
T5 2024.05	66.1	-	-	-	-	-	-	-	-	-
T5-large 2024.06	66.1	-	-	-	-	-	-	-	-	-
DeGLM-CoGLM 2024.05	66.08	70.58	52.65	-	-	-	-	-	-	-
GECTOR 2020.05	66	76.6	42.3	-	-	-	-	-	-	-
GECTOR-2024 2024.04	66	75	44.7	-	-	-	-	-	-	-
+ BIFI (ours) 2021.09	65.8	78	40.6	-	-	-	-	-	-	-
CTC-Copy 2024.04	65.5	72.6	47	-	-	-	-	-	-	-
EditScorer 2024.04	65.5	78.5	39.4	-	-	-	-	-	-	-
GECTOR XLNet 2023.10	65.34	77.49	40.15	-	-	-	-	-	-	-
LLaMA2 2024.05	65.33	68.43	55.3	-	-	-	-	-	-	-
GECTOR 2020.05	65.3	77.5	40.1	-	-	-	-	-	-	-
GECToR(XLNet) 2021.06	65.3	77.5	40.1	-	-	-	-	-	-	-
GECTOR (Omelianchuk et al., 2020) 2021.09	65.3	77.5	40.1	-	-	-	-	-	-	-
GECTOR (our base) 2021.09	65.3	77.5	40.1	-	-	-	-	-	-	-
Omelianchuk et al. (2020) 2022.03	65.3	77.5	40.1	-	-	-	-	-	-	-
DeBERTa(L) + RoBERTa(L) + XLNet(L) 2022.03	65.3	76.1	41.6	-	-	-	-	-	-	-
Omelianchuk et al. (2020) 2022.10	65.3	77.5	40.1	-	-	-	-	-	-	-
Omelianchuk et al. (2020) 2023.07	65.3	77.5	40.1	-	-	-	-	-	-	-
GECToR 2024.05	65.3	77.5	40.1	-	-	-	-	-	-	-
GECToR 2024.06	65.3	77.5	40.1	-	-	-	-	-	-	-
Kaneko et al. (2020) 2022.03	65.2	72.6	46.4	-	-	-	-	-	-	-
Rothe et al. (2021) 2023.07	65.1	-	-	-	-	-	-	-	-	-
T5-Large 2023.10	65.07	69.66	51.5	-	-	-	-	-	-	-
Kiyono et al. (2019) 2020.05	65	72.4	46.1	-	-	-	-	-	-	-
Kiyono et al. (2019) 2021.09	65	72.4	46.1	-	-	-	-	-	-	-
Kiyono et al. (2019) 2022.03	65	72.4	46.1	-	-	-	-	-	-	-
SOME 2023.10	65	68.39	54.23	-	-	-	-	-	-	-
Riken&Tohoku 2023.10	64.74	73.26	44.17	-	-	-	-	-	-	-
UEDIN-MS 2023.10	64.52	75.15	41.21	-	-	-	-	-	-	-
GPT-2 2023.10	64.47	68.3	52.65	-	-	-	-	-	-	-
AMR-GEC 2023.07	64.4	70.2	48.3	-	-	-	-	-	-	-
AMR-GEC 2023.07	64.4	70.3	48.2	-	-	-	-	-	-	-
Grundkiewicz et al. (2019) 2022.03	64.2	-	-	-	-	-	-	-	-	-
Grundkiewicz et al. (2019) 2019.10	64.16	-	-	-	-	-	-	-	-	-
GECTOR 2020.05	64	73.9	41.5	-	-	-	-	-	-	-
GECToR(RoBERTa) 2021.06	64	73.9	41.5	-	-	-	-	-	-	12.4
RoBERTa (L) 10K 2022.03	64	74.4	41.05	-	-	-	-	-	-	-
GECTOR ROBERTa 2023.10	64	73.91	41.66	-	-	-	-	-	-	-
GPT-4 + DeGLM 2024.05	63.7	66.4	54.81	-	-	-	-	-	-	-
Our approach (9+3) 2021.06	63.5	73.3	41.3	-	-	-	-	-	-	10.3
SynGEC 2022.10	63.5	70	46.2	-	-	-	-	-	-	-
Multi-Encoder 2024.05	63.5	71.3	44.3	-	-	-	-	-	-	-
LLaMA2 2024.05	63.47	67.24	51.84	-	-	-	-	-	-	-
Transformer 2019.10	63.4	-	-	-	-	-	-	-	-	-
Xu et al. (2019) 2019.10	63.2	-	-	-	-	-	-	-	-	-
Wan and Wan (2021) 2022.10	63.2	74.4	39.5	-	-	-	-	-	-	-
GECTOR 2020.05	63	72.1	42	-	-	-	-	-	-	-
Katsumata and Komachi (2020) 2023.07	63	69.9	45.1	-	-	-	-	-	-	-
VERNet 2023.10	62.85	74.08	39.12	-	-	-	-	-	-	-
Kaneko et al. (2020) 2022.03	62.6	69.2	45.6	-	-	-	-	-	-	-
Kaneko et al. (2020) 2022.10	62.6	69.2	45.6	-	-	-	-	-	-	-
Katsumata and Komachi (2020) 2022.10	62.6	69.3	45	-	-	-	-	-	-	-
Katsumata and Komachi (2020) 2023.07	62.6	69.3	45	-	-	-	-	-	-	-

Showing 100 of 218 rows