Skip to content

Commit

Permalink
Added results for PIE (Grammatical Error Correction using BERT), EMNL…
Browse files Browse the repository at this point in the history
…P-IJCNLP 2019 (sebastianruder#394)

* Included results for PIE

* Included results for PIE
  • Loading branch information
awasthiabhijeet authored and sebastianruder committed Nov 30, 2019
1 parent 5cbfa41 commit 739715e
Showing 1 changed file with 2 additions and 0 deletions.
2 changes: 2 additions & 0 deletions english/grammatical_error_correction.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,9 @@ The shared task setting restricts that systems use only publicly available datas
| Model | F0.5 | Paper / Source | Code |
| ------------- | :-----:| --- | :-----: |
| Transformer + Pre-train with Pseudo Data (Kiyono et al., EMNLP 2019) | 65.0 | [An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction](https://arxiv.org/abs/1909.00502) | NA |
| Sequence Labeling with edits using BERT, Faster inference (Ensemble) (Awasthi et al., EMNLP 2019) | 61.2 | [Parallel Iterative Edit Models for Local Sequence Transduction](https://www.aclweb.org/anthology/D19-1435.pdf) | [Official](https://github.com/awasthiabhijeet/PIE) |
| Copy-Augmented Transformer + Pre-train (Zhao and Wang, NAACL 2019) | 61.15 | [Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data](https://arxiv.org/pdf/1903.00138.pdf) | [Official](https://github.com/zhawe01/fairseq-gec) |
| Sequence Labeling with edits using BERT, Faster inference (Single Model) (Awasthi et al., EMNLP 2019) | 59.7 | [Parallel Iterative Edit Models for Local Sequence Transduction](https://www.aclweb.org/anthology/D19-1435.pdf) | [Official](https://github.com/awasthiabhijeet/PIE) |
| CNN Seq2Seq + Quality Estimation (Chollampatt and Ng, EMNLP 2018) | 56.52 | [Neural Quality Estimation of Grammatical Error Correction](https://aclweb.org/anthology/D18-1274) | [Official](https://github.com/nusnlp/neuqe/) |
| SMT + BiGRU (Grundkiewicz and Junczys-Dowmunt, 2018) | 56.25 | [Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation](https://aclweb.org/anthology/N18-2046)| NA |
| Transformer (Junczys-Dowmunt et al., 2018) | 55.8 | [Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task](https://aclweb.org/anthology/N18-1055)| [Official](https://github.com/grammatical/neural-naacl2018) |
Expand Down

0 comments on commit 739715e

Please sign in to comment.