Papers › Frustratingly Easy System Combination for Grammatical Error Correction

Frustratingly Easy System Combination for Grammatical Error Correction

1 Jul 2022NAACL 2022 7archive 2025-07-28

Muhammad Qorib, Seung-Hoon Na, Hwee Tou Ng

In this paper, we formulate system combination for grammatical error correction (GEC) as a simple machine learning task: binary classification. We demonstrate that with the right problem formulation, a simple logistic regression algorithm can be highly effective for combining GEC models. Our method successfully increases the F0.5 score from the highest base GEC system by 4.2 points on the CoNLL-2014 test set and 7.2 points on the BEA-2019 test set. Furthermore, our method outperforms the state of the art by 4.0 points on the BEA-2019 test set, 1.2 points on the CoNLL-2014 test set with original annotation, and 3.4 points on the CoNLL-2014 test set with alternative annotation. We also show that our system combination generates better corrections with higher F0.5 scores than the conventional ensemble.

PaperPDFCode

Code

nusnlp/esc officialmentioned in paperpytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Binary ClassificationGrammatical Error Correction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Grammatical Error Correction BEA-2019 (test) ESC F0.5 79.90 #3 of 19 Archive leaderboard report
Grammatical Error Correction CoNLL-2014 Shared Task ESC F0.5 69.51 #6 of 23 Archive leaderboard report
Grammatical Error Correction CoNLL-2014 Shared Task ESC Precision 81.48 #6 of 23 Archive leaderboard report
Grammatical Error Correction CoNLL-2014 Shared Task ESC Recall 43.78 #6 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections