Phrase-based SMT |
2016 |
[Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction] |
[code] |
Neural reinforcement learning |
2017 |
[Grammatical Error Correction with Neural Reinforcement Learning] |
|
Word-level SMT enhanced NNJMs + char-based SMT |
2017 |
[Connecting the Dots: Towards Human-Level Grammatical Error Correction] |
[code] |
First NMT-based approach |
2016 |
[Grammatical error correction using neural machine translation] |
|
SMEG |
2017 |
[Systematically Adapting Machine Translation for Grammatical Error Correction] |
[code] |
A nested attention (word and char attention) |
2017 |
[A Nested Attention Neural Hybrid Model for Grammatical Error Correction] |
|
Re-ranking N-best sentence (by SMT) with LSTM-based GED |
2017 |
[Neural Sequence-Labelling Models for Grammatical Error Correction] |
|
CNN-based Encder-Decoder approach |
2018 |
[A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction] |
[code] |
Fluency boosting learning |
2018 |
[Fluency Boost Learning and Inference for Neural Grammatical Error Correction] |
[code] ACL2018 |
Fluency boosting learning (added round-way error correction) |
2018 |
[Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study] |
[code] Microsoft Research Technical Report |
Hybrid SMT and NMT |
2018 |
[Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation] |
|
Copy-Augmented Architecture |
2019 |
[Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data] |
[code] |
Consider a few previous sentences |
2019 |
[Cross-Sentence Grammatical Error Correction] |
[code] |
PIE |
2019 |
[Parallel Iterative Edit Models for Local Sequence Transduction] |
[code] |
LaserTagger |
2019 |
[Encode, Tag, Realize: High-Precision Text Editing] |
[code] |
Pretrain by DAE + sequential transfer learning |
2019 |
[A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning] |
[code] BEA-2019: Kakao&Brain |
Use sentence-level error dectection |
2019 |
[The AIP-Tohoku System at the BEA-2019 Shared Task] |
BEA-2019: AIP-Tohoku |
Four CNN + eight Transformer |
2019 |
[The LAIX Systems in the BEA-2019 GEC Shared Task] |
BEA-2019: LAIX |
Combine Transformer+CNN with FST + Re-ranking |
2019 |
[Neural and FST-based approaches to grammatical error correction] |
BEA-2019: CAMB-CLED |
Transformer seq2seq + BERT re-ranker |
2019 |
[TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track] |
BEA-2019: TMU |
Apply noisy channel with BERT and GPT-2 as LM |
2019 |
[Noisy Channel for Low Resource Grammatical Error Correction] |
BEA-2019: Siteimprove |
Use Finite State Transducers |
2019 |
[Neural Grammatical Error Correction with Finite State Transducers] |
|
GECToR |
2020 |
[GECToR – Grammatical Error Correction: Tag, Not Rewrite] |
[code] |
BERT-fuse |
2020 |
[Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction] |
[code] |
Adversarial approach (G:seq2seq D:sentence-pair classification) |
2020 |
[Adversarial Grammatical Error Correction] |
|
Erroneous span correction and detection |
2020 |
[Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction] |
|
Document-level approach |
2020 |
[Document-level grammatical error correction] |
[code] |
Seq2Edits |
2020 |
[Seq2Edits: Sequence Transduction Using Span-level Edit Operations] |
[code] |
Beam search considering copy probability |
2020 |
[Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction] |
|
BART-based |
2020 |
[Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model] |
[code] |
VERNet |
2021 |
[Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction] |
[code] |
Shallow Aggressive Decoding |
2021 |
[Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding] |
[code] |
T5-based |
2021 |
[A Simple Recipe for Multilingual Grammatical Error Correction] |
[code] |
GAN-like sequence labeling |
2021 |
[Grammatical Error Correction as GAN-like Sequence Labeling] |
|
Diversity-Driven Combination (DDC) |
2021 |
[Diversity-Driven Combination for Grammatical Error Correction] |
[code] |
Select a system for each error type with IP |
2021 |
[System Combination for Grammatical Error Correction Based on Integer Programming] |
[code] |
Use multiclass GED for Transformer seq2seq and reranking |
2021 |
[Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems] |
|
GEC for writing improvement model adapted to the writer’s L1 |
2021 |
[Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models] |
[code] |
Constrastive Leaning approach |
2021 |
[Grammatical Error Correction with Contrastive Learning in Low Error Density Domains] |
[code] |
Sequence Span Rewriting |
2021 |
[Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting] |
|
Dependent Self-Attention (DSA) |
2021 |
[Grammatical Error Correction with Dependency Distance] |
|
|
2022 |
Interpretability for Language Learners Using Example-Based Grammatical Error Correction |
[code] |
|
2022 |
Type-Driven Multi-Turn Corrections for Grammatical Error Correction |
[code] |
GECToR Large |
2022 |
Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction |
[code] [Author's Master Thesis] |