Papers › A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
Shamil Chollampatt, Hwee Tou Ng
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neural approaches on this task as well as strong statistical machine translation-based systems with neural and task-specific features trained on the same data. Our analysis shows the superiority of convolutional neural networks over recurrent neural networks such as long short-term memory (LSTM) networks in capturing the local context via attention, and thereby improving the coverage in correcting grammatical errors. By ensembling multiple models, and incorporating an N-gram language model and edit features via rescoring, our novel method becomes the first neural approach to outperform the current state-of-the-art statistical machine translation-based approach, both in terms of grammaticality and fluency.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Grammatical Error Correction | CoNLL-2014 Shared Task | CNN Seq2Seq | F0.5 | 54.79 | #23 of 23 | Archive leaderboard | report |
| Grammatical Error Correction | CoNLL-2014 Shared Task (10 annotations) | CNN Seq2Seq | F0.5 | 70.14 | #3 of 3 | Archive leaderboard | report |
| Grammatical Error Correction | JFLEG | CNN Seq2Seq | GLEU | 57.47 | #6 of 6 | Archive leaderboard | report |
| Grammatical Error Correction | Restricted | CNN Seq2Seq | F0.5 | 70.14 (measured by Ge et al., 2018) | #1 of 4 | Archive leaderboard | report |
| Grammatical Error Correction | _Restricted_ | CNN Seq2Seq | GLEU | 57.47 | #2 of 2 | 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