# Grammatical Error Correction on CoNLL-10

Source: [Grammatical Error Correction on CoNLL-10](<https://www.sota2.com/research/sota/grammatical-error-correction-on-conll-10>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:42:44.238Z

Evaluation of Grammatical Error Correction performance on the CoNLL-10 dataset, measured using metrics such as F0.5.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Grammatical Error Correction |
| Dataset (including any stated split) | CoNLL-10 |
| Metric | F0.5 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [F0.5 Score](<https://www.sota2.com/research/sota/grammatical-error-correction-on-conll-10.md?metric=F0.5%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/grammatical-error-correction-on-conll-10.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/grammatical-error-correction-on-conll-10.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F0.5 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Base + FB learning | 76.88 | Not recorded | 68fa649c1e209131cea058c5 |
| Base + FB learning | 76.88 | Not recorded | 68fa649c1e209131cea058c5 |
| Base + FB learning and inference | 75.72 | Not recorded | 68fa649c1e209131cea058c5 |
| Base + FB learning and inference | 75.72 | Not recorded | 68fa649c1e209131cea058c5 |
| Base convolutional seq2seq | 73.19 | Not recorded | 68fa649c1e209131cea058c5 |
| Base convolutional seq2seq | 73.19 | Not recorded | 68fa649c1e209131cea058c5 |
| NUS18 | 70.14 | Not recorded | 68fa649c1e209131cea058c5 |
| NUS18 | 70.14 | Not recorded | 68fa649c1e209131cea058c5 |
| NUS17 | 69.12 | Not recorded | 68fa649c1e209131cea058c5 |
| NUS17 | 69.12 | Not recorded | 68fa649c1e209131cea058c5 |
| AMU16 | 66.83 | Not recorded | 68fa649c1e209131cea058c5 |
| VT16 | 62.45 | Not recorded | 68fa649c1e209131cea058c5 |
| NUS16 | 60.36 | Not recorded | 68fa649c1e209131cea058c5 |
| CAMB14 | 54.3 | Not recorded | 68fa649c1e209131cea058c5 |
| CUUI | 51.79 | Not recorded | 68fa649c1e209131cea058c5 |
| AMU14 | 50.17 | Not recorded | 68fa649c1e209131cea058c5 |

### Base + FB learning

F0.5 Score: 76.88. Result ID: 698c4e4837894ef7d9cd5ec3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: {"fluency boost learning":true}. This record does not assert independent reproduction.

### Base + FB learning

F0.5 Score: 76.88. Result ID: 698c4e4837894ef7d9cd5edd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: {"training":"fluency boost learning"}. This record does not assert independent reproduction.

### Base + FB learning and inference

F0.5 Score: 75.72. Result ID: 698c4e4837894ef7d9cd5ec4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: {"fluency boost learning":true,"fluency boost inference":true}. This record does not assert independent reproduction.

### Base + FB learning and inference

F0.5 Score: 75.72. Result ID: 698c4e4837894ef7d9cd5ede.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: {"training":"fluency boost learning","inference":"fluency boost inference"}. This record does not assert independent reproduction.

### Base convolutional seq2seq

F0.5 Score: 73.19. Result ID: 698c4e4837894ef7d9cd5ec2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Base convolutional seq2seq

F0.5 Score: 73.19. Result ID: 698c4e4837894ef7d9cd5edc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Implementation](<https://github.com/getao/human-performance-gec>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NUS18

F0.5 Score: 70.14. Result ID: 698c4e4837894ef7d9cd5ec1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bee.md>)

[Implementation](<https://github.com/nusnlp/mlconvgec2018>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NUS18

F0.5 Score: 70.14. Result ID: 698c4e4837894ef7d9cd5edb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bee.md>)

[Implementation](<https://github.com/nusnlp/mlconvgec2018>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NUS17

F0.5 Score: 69.12. Result ID: 698c4e4837894ef7d9cd5ec0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NUS17

F0.5 Score: 69.12. Result ID: 698c4e4837894ef7d9cd5eda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AMU16

F0.5 Score: 66.83. Result ID: 698c4e4837894ef7d9cd5ebe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d41e209131ce9fb644.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VT16

F0.5 Score: 62.45. Result ID: 698c4e4837894ef7d9cd5ebc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NUS16

F0.5 Score: 60.36. Result ID: 698c4e4837894ef7d9cd5ebf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CAMB14

F0.5 Score: 54.3. Result ID: 698c4e4837894ef7d9cd5eba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CUUI

F0.5 Score: 51.79. Result ID: 698c4e4837894ef7d9cd5ebb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AMU14

F0.5 Score: 50.17. Result ID: 698c4e4837894ef7d9cd5ebd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058c5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
