Shadowgraph
TrendingAbout
Sign in

gotutiyan/GEC-Info

Repository to collect and categorize Grammatical Error Correction papers.

127

85 commits

updated Aug 16, 2026

See the code

README

GEC Information

Policy

  • This repository aims to collect and categorize GEC (Grammatical Error Correction) papers.
  • Unlike NLP-progress, GEC-Info does not consider performance on benchmarks.
    • Authors and conferences are also not be considered.
  • The papers are limited to refereed papers in international conferences for now.
    • This is not the case for survey papers.

Contributing

  • Pull Requests for adding papers are accepted. Please make a commit changing only lines regarding the addition of papers (and take care of changing by auto-formatting).
  • You can also request to add papers as an issue.

It can also be viewed on GitHub Pages

Overview

Surveys

TitleYearPageNote
"Automated Grammatical Error Correction: A Comprehensive Review"2017[paper]
"A Comprehensive Survey of Grammar Error Correction"2020[paper]
"Recent Trends in the Use of Deep Learning Models for Grammar Error Handling"2020[paper]
"Grammatical Error Correction: A Survey of the State of the Art"2022[paper]

Shared Tasks

NameYearPaperNote
HOO 20112011[paper][website]
HOO 20122012[paper][website]
CoNLL-20132013[paper][website]
CoNLL-20142014[paper][website] [system outputs]
BEA-20192019[paper][website] [system outpus]
BHASHA 20252025Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025Indian Languages. Teams: [Niyamika] [Horizon] [A3-108] [DLRG] [akhilrajeevp]

Libraries

NameYearPaperNote
UnifiedGEC2025UnifiedGEC: Integrating Grammatical Error Correction Approaches for Multi-languages with a Unified Framework[code]
gec-metrics2025gec-metrics: A Unified Library for Grammatical Error Correction Evaluation[code]

Datasets

For Training (Real Data)

NameYearPaperNote
EFCamDat2014Automatic Linguistic Annotation ofLarge Scale L2 Databases: The EF-Cambridge Open Language Database(EFCamDat) The EF Cambridge Open Language Database (efcamdat) Information for Users[download v2]
GitHub Typo Corpus2019GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors[download]
W&I+LOCNESS on BEA2019 Shared Task2019Developing an Automated Writing Placement System for ESL Learners [direct download]
FCE2011A New Dataset and Method for Automatically Grading ESOL Texts[direct download]
NUCLE2013Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English[download]
ICNALE2013The ICNALE and Sophisticated Contrastive Interlanguage Analysis of Asian Learners of English[download]
Lang-82011Mining Revision Log of Language Learning SNS for Automated Japanese Error Correction of Second Language Learners[website] [download: Fill this form]
Related tools are useful. See the [Other Tools] for the details.

For Training (Pseudo/Systhetic Data)

NameYearPaperNote
PIE-synthetic2019Parallel Iterative Edit Models for Local Sequence Transduction[download]
OmniGEC2025Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction[HF datasets], [code]. Czech, English, Estonian, German, Greek, Icelandic, Italian, Latvian, Slovene, Swedish, and Ukrainian

For Evaluation

NameYearPaperNote
KJ2011Creating a manually error-tagged and shallow-parsed learner corpus[download]
CoNLL-20132013The CoNLL-2013 Shared Task on Grammatical Error Correction[direct download]
CoNLL-20142014The CoNLL-2014 Shared Task on Grammatical Error Correction[direct download]
10 additional annotations for the CoNLL142015How Far are We from Fully Automatic High Quality Grammatical Error Correction?[direct download]
8 additional annotations for the CoNLL142016Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality[download]
JFLEG2017JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction[download]
GMEG-Data2019Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses[code]
CWEB2020Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses[download]
ErAConD2021ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction[data]
Training dataset is also included.
RobustGEC2023RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation[code]
CSW Lang-8 Dataset2024Grammatical Error Correction for Code-Switched Sentences by Learners of English[code/data]
CTSEG2025Targeted Syntactic Evaluation for Grammatical Error Correction[data]

Performance measures

Reference-based

NameYearPaperNote
M^2 Scorer2012Better Evaluation for Grammatical Error Correction[code]
It is often used to evaluate CoNLL-2013 and CoNLL-2014.
GLEU2015Ground Truth for Grammatical Error Correction Metrics
GLEU Without Tuning		[code]
It is often used to evaluate JFLEG.
I-measure2015Towards a standard evaluation method for grammatical error detection and correction[code]
Code is available only python 2.x.
ERRANT2016Automatic Extraction of Learner Errors in ESL Sentences Using Linguistically Enhanced Alignments
Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction		[code]
It is often used to evaluate BEA-2019.
GMEG-Metric2019Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses[code]
Ridge regression using existing metrics (e.g. ERRANT, GLEU) as features.
GoToScorer2019Taking the Correction Difficulty into Account in Grammatical Error Correction Evaluation[code]
It can be evaluated systems considering error correction difficulty.
PT-M22022Revisiting Grammatical Error Correction Evaluation and Beyond[code]
CLEME2023CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction[code]
GREEN2024n-gram F-score for Evaluating Grammatical Error Correction[code]
2025Refined Evaluation for End-to-End Grammatical Error Correction Using an Alignment-Based Approach[website]
CLEME2.02025CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction[code]
ERRANT extended to multiple languages2025Multilingual Grammatical Error Annotation: Combining Language-Agnostic Framework with Language-Specific Flexibility[code]

Reference-free

Keywords / OverviewYearPaperNote
Scoring by counting the errors2016There’s No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction[code]
Fluency + grammaticality + meaning preservation2017Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems
USim2018Reference-less Measure of Faithfulness for Grammatical Error Correction[code]
SOME2020SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction[code]
Scribendi Score2021Is this the end of the gold standard? A straightforward reference-less grammatical error correction metric[Unofficial code]
IMPARA2022IMPARA: Impact-Based Metric for GEC Using Parallel Data[code]
2024Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction
IMPARA-GED2025IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator[Official model]
2025LLM-based post-editing as reference-free GEC evaluation

Meta-evaluation

Keywords / OverviewYearPaperNote
Re-rank the CoNLL14 systems by human evaluation2015Human Evaluation of Grammatical Error Correction Systems[code]
Reassess M^2, I-measure, GLEU by comparing human evaluation2018A Reassessment of Reference-Based Grammatical Error Correction Metrics[code]
MAEGE2018Automatic Metric Validation for Grammatical Error Correction[code]
SEEDA2024Revisiting Meta-evaluation for Grammatical Error Correction[code]

Quality Estimation

Keywords / OverviewYearPaperNote
2022ProQE: Proficiency-wise Quality Estimation dataset for Grammatical Error Correction

Models

Before Neural (E.g., SMT)

Keywords / OverviewYearPaperNote
2006Correcting ESL Errors Using Phrasal SMT Techniques
2009Using First and Second Language Models to Correct Preposition Errors in Second Language Authoring
2010Generating Confusion Sets for Context-Sensitive Error Correction
2011Correcting Semantic Collocation Errors with L1-induced Paraphrases
2012Tense and Aspect Error Correction for ESL Learners Using Global Context
2012Exploring Grammatical Error Correction with Not-So-Crummy Machine Translation
2014Grammatical error correction using hybrid systems and type filteringCoNLL2014: CAMB
2014The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine TranslationCoNLL2014: AMU
2014The Illinois-Columbia System in the CoNLL-2014 Shared TaskCoNLL2014: CUUI
2014RACAI GEC – A hybrid approach to Grammatical Error CorrectionCoNLL2014: RAC
2014Grammatical Error Detection Using Tagger DisagreementCoNLL2014: UFC
2014CoNLL 2014 Shared Task: Grammatical Error Correction with a Syntactic N-gram Language Model from a Big CorporaCoNLL2014: IPN
2014Tuning a Grammar Correction System for Increased PrecisionCoNLL2014: IITB
2014POSTECH Grammatical Error Correction System in the CoNLL-2014 Shared TaskCoNLL2014: POST
2014Grammatical Error Detection and Correction using a Single Maximum Entropy ModelCoNLL2014: SJTU
2014Factored Statistical Machine Translation for Grammatical Error CorrectionCoNLL2014: UMC
2014NTHU at the CoNLL-2014 Shared TaskCoNLL2014: NTHU
2014A Unified Framework for Grammar Error CorrectionCoNLL2014: PKU
2016Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction
2016Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models
Phrase-based SMT2016Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction[code]
Word-level SMT enhanced NNJMs + char-based SMT2017Connecting the Dots: Towards Human-Level Grammatical Error Correction[code]
SMEG2017Systematically Adapting Machine Translation for Grammatical Error Correction[code]

Encoder-Decoder

Keywords / OverviewYearPaperNote
First NMT-based approach2016Grammatical error correction using neural machine translation
2016Neural Network Translation Models for Grammatical Error Correction
Neural reinforcement learning2017Grammatical Error Correction with Neural Reinforcement Learning[code]
A nested attention (word and char attention)2017A Nested Attention Neural Hybrid Model for Grammatical Error Correction
Re-ranking N-best sentence (by SMT) with LSTM-based GED2017Neural Sequence-Labelling Models for Grammatical Error Correction
Hybrid SMT and NMT2018Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
CNN-based Encder-Decoder approach2018A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction[code]
Fluency boosting learning2018Fluency Boost Learning and Inference for Neural Grammatical Error Correction[code] [arXiv]
Copy-Augmented Architecture2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data[code]
Consider a few previous sentences2019Cross-Sentence Grammatical Error Correction[code]
Use sentence-level error dectection2019The AIP-Tohoku System at the BEA-2019 Shared TaskBEA-2019: AIP-Tohoku
Four CNN + eight Transformer2019The LAIX Systems in the BEA-2019 GEC Shared TaskBEA-2019: LAIX
Combine Transformer+CNN with FST + Re-ranking2019Neural and FST-based approaches to grammatical error correctionBEA-2019: CAMB-CLED
Transformer seq2seq + BERT re-ranker2019TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted TrackBEA-2019: TMU
Apply noisy channel with BERT and GPT-2 as LM2019Noisy Channel for Low Resource Grammatical Error CorrectionBEA-2019: Siteimprove
Use Finite State Transducers2019Neural Grammatical Error Correction with Finite State Transducers
BERT-fuse2020Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction[code]
Adversarial approach (G:seq2seq D:sentence-pair classification)2020Adversarial Grammatical Error Correction
Erroneous span correction and detection2020Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
Document-level approach2020Document-level grammatical error correction[code]
Beam search considering copy probability2020Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction
BART-based2020Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model[code]
VERNet2021Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction[code]
Shallow Aggressive Decoding2021Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding[code]
T5-based2021A Simple Recipe for Multilingual Grammatical Error Correction[code]
Use multiclass GED for Transformer seq2seq and reranking2021Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems
GEC for writing improvement model adapted to the writer’s L12021Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models[code]
Constrastive Leaning approach2021Grammatical Error Correction with Contrastive Learning in Low Error Density Domains[code]
Sequence Span Rewriting2021Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
Pretrain by DAE + sequential transfer learning2019A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning[code]
BEA-2019: Kakao&Brain
Dependent Self-Attention (DSA)2021Grammatical Error Correction with Dependency Distance
A GEC model using only 11.6MB2021An efficient system for grammatical error correction on mobile devices
LM-Critic2021LM-Critic: Language Models for Unsupervised Grammatical Error Correction[code]
Supervised setting is also performed
2022Interpretability for Language Learners Using Example-Based Grammatical Error Correction[code]
2022Position Offset Label Prediction for Grammatical Error Correction
SynGEC2022SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser[code]
EdiT52022EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start[code]
GEC-DePenD2023GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding[code]
TemplateGEC2023TemplateGEC: Improving Grammatical Error Correction with Detection Template[code]
LET2023LET: Leveraging Error Type Information for Grammatical Error Correction
2023Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction
Use speech information2023Improving Grammatical Error Correction with Multimodal Feature Integration[code]
2023Improving Autoregressive Grammatical Error Correction with Non-autoregressive Models
2023Unsupervised Grammatical Error Correction Rivaling Supervised Methods[code]
2024No Error Left Behind: Multilingual Grammatical Error Correction with Pre-trained Translation Models
EDU Copy Mechanism2024Improving Copy-oriented Text Generation via EDU Copy Mechanism
2024Efficient and Interpretable Grammatical Error Correction with Mixture of Experts[code]
2025InstructGEC: Enhancing Unsupervised Grammatical Error Correction with Instruction Tuning
CxGGEC2025CxGGEC: Construction-Guided Grammatical Error Correction

Tagging / Non-autogressive

Keywords / OverviewYearPaperNote
LSTM tagger for word coice task2019Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems[code]
PIE2019Parallel Iterative Edit Models for Local Sequence Transduction[code]
LaserTagger2019Encode, Tag, Realize: High-Precision Text Editing[code]
GECToR2020GECToR – Grammatical Error Correction: Tag, Not Rewrite[code]
Seq2Edits2020Seq2Edits: Sequence Transduction Using Span-level Edit Operations[code]
GAN-like sequence labeling2021Grammatical Error Correction as GAN-like Sequence Labeling
GECToR Large2022Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction[code] [Author's Master Thesis]
2021Efficient Grammatical Error Correction with Hierarchical Error Detections and Correction[code]
2022Type-Driven Multi-Turn Corrections for Grammatical Error Correction[code]
2023An Extended Sequence Tagging Vocabulary for Grammatical Error Correction[code]

Large Language Model

Keywords / OverviewYearPaperNote
5-gram LM based approach2018Language Model Based Grammatical Error Correction without Annotated Training Data[code]
Use Finite State Transducers2019Neural Grammatical Error Correction with Finite State Transducers
Use LM (BERT, GPT-1,2)2019The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction
2023Reducing Sequence Length by Predicting Edit Spans with Large Language Models
2023Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods
2024Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency
2024GPT-3.5 for Grammatical Error CorrectionTarget languages: CZ, DE, EN, RU, SV, UA
2024Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction[code]
mEdIT2024mEdIT: Multilingual Text Editing via Instruction Tuning[code]
DeCoGLM2024Detection-Correction Structure via General Language Model for Grammatical Error Correction[code]
For code-switched text2024LLM-based Code-Switched Text Generation for Grammatical Error Correction[code]
EPO2025Edit-Wise Preference Optimization for Grammatical Error Correction
2024Prompting open-source and commercial language models for grammatical error correction of English learner text[code]
2025Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction[code]
2025Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction[code]
2025Adapting LLMs for Minimal-edit Grammatical Error Correction[code]
2025Leveraging What’s Overfixed: Post-Correction via LLM Grammatical Error Overcorrection

Ensembles / Post-processing

Keywords / OverviewYearPaperNote
Use MENT2014System Combination for Grammatical Error Correction
2016Grammatical Error Correction: Machine Translation and Classifiers
2019Learning to combine Grammatical Error Corrections[code]
Diversity-Driven Combination (DDC)2021Diversity-Driven Combination for Grammatical Error Correction[code]
Select a system for each error type with IP2021System Combination for Grammatical Error Correction Based on Integer Programming[code]
2022Frustratingly Easy System Combination for Grammatical Error Correction[code]
EditScorer2022Improved grammatical error correction by ranking elementary edits[code]
GRECO2023System Combination via Quality Estimation for Grammatical Error Correction[code]
2024Improving Grammatical Error Correction by Correction Acceptability Discrimination

Strategies

This includes methods such as decoding techniques and approaches that modify the loss function while keeping the model architecture unchanged.

Keywords / OverviewYearPaperNote
2012A Beam-Search Decoder for Grammatical Error Correction
2016Discriminative Reranking for Grammatical Error Correction with Statistical Machine Translation
2016Candidate re-ranking for SMT-based grammatical error correction
Some methods that can be adapted neural MT2018Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task[code]
Iterative decoding2018Weakly Supervised Grammatical Error Correction using Iterative Decoding
2019Controlling Grammatical Error Correction Using Word Edit Rate
Add adversarial examples continually2020Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples
Cross-lingual Transfer Learning2020Cross-lingual Transfer Learning for Grammatical Error Correction
Data Weighted Training Strategies2020Data Weighted Training Strategies for Grammatical Error Correction
Align-and-Predict Decoding2022Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error Correction[code]
2023Mitigating Exposure Bias in Grammatical Error Correction with Data Augmentation and Reweighting[code]
BTR2023Bidirectional Transformer Reranker for Grammatical Error Correction[code]
2023Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule
MainGEC2023Grammatical Error Correction via Mixed-Grained Weighted Training
2023Improving Seq2Seq Grammatical Error Correction via Decoding Interventions[code]
2024Multi-pass Decoding for Grammatical Error Correction

Data Augmentation

Keywords / OverviewYearPaperNote
Make artificial errors in a probabilistic manner2014Generating artificial errors for grammatical error correction
Back translation2016Improving Neural Machine Translation Models with Monolingual Data
SMT based MT + pattern extraction2017Artificial Error Generation with Machine Translation and Syntactic Patterns
Diverse back translation with noisy beam search2018Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction
MAGEC2019Minimally-Augmented Grammatical Error CorrectionSupervised setting is also performed
DirectNoise2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled DataThe method was first called "DirectNoise" by [kiyono+ 2019]?
Substituting words using confusion sets2019Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data[synthetic data]
BEA-2019: UEDIN-MS
Error+Context Dictionary2019Improving Precision of Grammatical Error Correction with a Cheat SheetBEA-2019: Buffalo
Use Google Translate for making pseudo data2019(Almost) Unsupervised Grammatical Error Correction using a Synthetic Comparable CorpusBEA-2019: TMU in Low Resource
Inverted Spellchecker + Patterns+POS2019A Comparative Study of Synthetic Data Generation Methods for Grammatical Error Correction
Methods for erroneous data generation2019Erroneous data generation for Grammatical Error CorrectionBEA-2019: Shuyao
Wikipedia revision & Wikipedia round-trip translation2019Corpora Generation for Grammatical Error Correction
Create confusion sets by edit distance, word embeddings, spell-breaking2019Minimally-Augmented Grammatical Error CorrectionSupervised setting is also performed
Explore methods to make pseude data, seed corpus, training settings2019An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction[code]
2020Massive Exploration of Pseudo Data for Grammatical Error Correction
Control error rates and error types by rule-based corruption and filtered back-translation2020Controllable Data Synthesis Method for Grammatical Error Correction
Use machine translation pairs2020Improving Grammatical Error Correction with Machine Translation Pairs
Edit latent representation2020Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation
Consider learner’s error tendency2020Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency
Tagged corruption2021Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models[code]
Use 188 modules2021Various Errors Improve Neural Grammatical Error Correction[code]
Use real error petterns and linguistic knowledge2021Data Augmentation of Incorporating Real Error Patterns and Linguistic Knowledge for Grammatical Error Correction
Divide non-English sentence into chunks → translate to English for each of them → concatenate2021Grammatical Error Generation Based on Translated Fragments
2023Grammatical Error Correction through Round-Trip Machine Translation
TransGEC2023TransGEC: Improving Grammatical Error Correction with Translationese[code]
Focus on gender bias2023Gender-Inclusive Grammatical Error Correction through Augmentation[code]
2023Training for Grammatical Error Correction Without Human-Annotated L2 Learners’ Corpora
MixEdit2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction[code]
2024Synthetic Data Generation for Low-resource Grammatical Error Correction with Tagged Corruption Models
2024Improving Grammatical Error Correction via Contextual Data Augmentation[code]
2024To Err Is Human, but Llamas Can Learn It Too[code]
2025Large Language Models are Good Annotators for Type-aware Data Augmentation in Grammatical Error Correction[code]
2025Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages
2025Low-Resource Grammatical Error Correction: Selective Data Augmentation with Round-Trip Machine Translation[code]. experiments Include Russian and Ukrainian.

Data Cleaning

Keywords / OverviewYearPaperNote
A Self-Refinement Strategy for Noise Reduction2020A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction
cLang8 (Cleaned Lang-8)2021A Simple Recipe for Multilingual Grammatical Error Correction[code]

Analyses

Keywords / OverviewYearPaperNote
2011Algorithm Selection and Model Adaptation for ESL Correction Tasks
2012The Effect of Learner Corpus Size in Grammatical Error Correction of ESL Writings
2015How Far are We from Fully Automatic High Quality Grammatical Error Correction?
Human annotation focused on fluency2016Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality[code]
2017GEC into the future: Where are we going and how do we get there?
2018Inherent Biases in Reference-based Evaluation for Grammatical Error Correction[code]
2018Assessing Grammatical Correctness in Language Learning
Quality estimation (and re-ranking using estimated score)2018Neural Quality Estimation of Grammatical Error Correction[code]
Evaluate four systems (SMT, CNN, LSTM, Transformer) for six corpora (CoNLL13&14, FCE, JFLEG, KJ, ICNALE)2019Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models — Is Single-Corpus Evaluation Enough?
Compare CNN, Transformer, PRPN, ON-LSTM as back-translation models2019The Unbearable Weight of Generating Artificial Errors for Grammatical Error Correction
GEC for post-processing2019Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
CGOP2020Comparison of the Evaluation Metrics for Neural Grammatical Error Correction With OvercorrectionMetric Considering overcorrection
Create new gold data by post-editing system outputs2021How Good (really) are Grammatical Error Correction Systems?
Explore whether models have grammatical knowledge with Known-setting and Unknown-setting2021Do Grammatical Error Correction Models Realize Grammatical Generalization?
Compare CNN, LSTM, transformer or combinations of them as BT models2021Comparison of Grammatical Error Correction Using Back-Translation Models
2022Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
2022Grammatical Error Correction: Are We There Yet?
2022Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?[code]
2023ChatBack: Investigating Methods of Providing Grammatical Error Feedback in a GUI-based Language Learning Chatbot
2023A Closer Look at k-Nearest Neighbors Grammatical Error Correction
2023Grammatical Error Correction for Sentence-level Assessment in Language Learning
2023Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
2024Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models][code]
2024Likelihood-based Mitigation of Evaluation Bias in Large Language Models
2025Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?[code]
2025Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction[code]
2025Reliability Crisis of Reference-free Metrics for Grammatical Error Correction[code]

Spoken Domain

Keywords / OverviewYearPaperNote
2019AUTOMATIC GRAMMATICAL ERROR DETECTION OF NON-NATIVE SPOKEN LEARNER ENGLISH
2020Grammatical error detection in transcriptions of spoken English
Disfluency detection (DD) model2020Spoken Language ‘Grammatical Error Correction’
2022On Assessing and Developing Spoken ’Grammatical Error Correction’ Systems

Applications

NameYearPaperNote
GECko++GECko+: a Grammatical and Discourse Error Correction Tool[website] [code]
An English assiting tool. Correction grammatical error and re-ordering sentences automatically.
MiSS2021MiSS: An Assistant for Multi-Style Simultaneous Translation[website] [demo video]
ALLECS2023ALLECS: A Lightweight Language Error Correction System[website] [code]
2023Doolittle: Benchmarks and Corpora for Academic Writing Formalization[code]
2025Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore[code]

Projects

NameWebsite
GramFormer[GitHub]

Other Tools

NameCodeNote
Lang8-NAIST-extractor[code]Scripts for extracting error-correct pairs from the Lang-8 Corpus.
M2Converter[code]Scripts for converting m2 file into source file and target file.
EFCamDat-Preprocess[code]

Other materials

NamePaperNote
NLP-progresswebsite
The performance ranking on some datasets.
A Crash Course in Automatic Grammatical Error Correction[paper]materials
The tutorial about GEC in COLING2020.
Chunngai/gec-papersgithub

Related Tasks

Grammatical Error Detection

Keywords / OverviewYearPaperNote
2003Automatic Error Detection in the Japanese Learners’ English Spoken Data
2006Detecting errors in English article usage by non-native speakers
2008The Ups and Downs of Preposition Error Detection in ESL Writing
2010Evaluating performance of grammatical error detection to maximize learning effect
A weighted measure according to crowdsourcing results (for GED)2011They Can Help: Using Crowdsourcing to Improve the Evaluation of Grammatical Error Detection Systems
2014Detecting Learner Errors in the Choice of Content Words Using Compositional Distributional Semantics
2016Compositional Sequence Labeling Models for Error Detection in Learner Writing
2017Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings[code]
2018Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection[code]
Bi-LSTM with contextual word embeddings2019Context is Key: Grammatical Error Detection with Contextual Word Representations
Multi-head and multi-layer attention2019Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection
2021Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical Errors
2022Probing for targeted syntactic knowledge through grammatical error detection[code]
2024Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection[data]
2025Oddballness: universal anomaly detection with language models[code]

Feedback Comment Generation

Keywords / OverviewYearPaperNote
2014Correcting Preposition Errors in Learner English Using Error Case Frames and Feedback Messages
English grammar checker with feedback in Japanese2018Grammatical Error Checker for Japanese Learners of EnglishThis is not a research as a feedback comment generation, but I classify it here for now
2019Toward a Task of Feedback Comment Generation for Writing Learning
2020Creating Corpora for Research in Feedback Comment Generation
2021Shared Task on Feedback Comment Generation for Language Learners
2023Template-guided Grammatical Error Feedback Comment Generation

Explainable Grammatical Error Correction

  • Studies to explain the reasons for and intentions of error correction.
Keywords / OverviewYearPaperNote
EXPECT2023Enhancing Grammatical Error Correction Systems with Explanations[code]
XGEC dataset2024Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction[data]
GEE2024GEE! Grammar Error Explanation with Large Language Models[code]

Document-level Revision

Keywords / OverviewYearPaperNote
TETRA2024Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond[code]

Other Languages

Arabic

Keywords / OverviewYearPaperNote
Arabic Learner Corpus2013Arabic Learner Corpus v1: A New Resource for Arabic Language Research[website]
QALB2014Large Scale Arabic Error Annotation: Guidelines and Framework[QALB Project Website]
QALB 2014 Shared Task2014The First QALB Shared Task on Automatic Text Correction for Arabic[website]
QALB 2015 Shared Task2015The Second QALB Shared Task on Automatic Text Correction for Arabic
ARETA2021Automatic Error Type Annotation for Arabic[code]
2023Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation[code]
2023Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction
2025ARWI: Arabic Write and Improve[website]
2025Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study[code]
Nahw2026Nahw: A Comprehensive Benchmark of Arabic Grammar Understanding, Error Detection, Correction, and Explanation[Data]

Bangla

Keywords / OverviewYearPaperNote
2021Development of Bangla Spell and Grammar Checkers: Resource Creation and Evaluation
2025Leveraging LLMs for Bangla Grammar Error Correction: Error Categorization, Synthetic Data, and Model Evaluation[code]

Chinese

Keywords / OverviewYearPaperNote
2013Chinese Spelling Checker Based on Statistical Machine Translation
2014Chinese Word Ordering Errors Detection and Correction for Non-Native Chinese Language Learners
2015Improving Chinese Grammatical Error Correction with Corpus Augmentation and Hierarchical Phrase-based Statistical Machine Translation
NLPCC-2018 Shared Task2018Overview of the NLPCC 2018 Shared Task: Grammatical Error Correction[data]
Two-stage: Spell checker → seq2seq2019A Two-Stage Model for Chinese Grammatical Error Correction
CNN-based seq2seq2019Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model
MaskGEC2020MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking
2020Chinese Grammatical Error Detection Based on BERT Model
2020BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis
2020Heterogeneous Recycle Generation for Chinese Grammatical Error Correction
NLPTEA-2020 Shared Task2020Overview of NLPTEA-2020 Shared Task for Chinese Grammatical Error Diagnosis
Tail-to-Tail Non-Autoregressive Sequence Prediction2021Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
2021"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction
2022Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students
2022MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction[code]
2022Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error Generation[code]
2022String Editing Based Chinese Grammatical Error Diagnosis
CLG2022Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction[code]
2022From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction
FCGEC2022FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction[code]
2023Are Pre-trained Language Models Useful for Model Ensemble in Chinese Grammatical Error Correction?[code]
2023Focal Training and Tagger Decouple for Grammatical Error Correction
NaSGEC2023NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts[code]
TLM2023TLM: Token-Level Masking for Transformers[code]
2024LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction[code]
Alirector2024Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector[code]
2024Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction[code]
2024Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method[code]
2025Improving Automatic Grammatical Error Annotation for Chinese Through Linguistically-Informed Error Typology[website]
2025A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction[code]
VisCGEC2025VisCGEC: Benchmarking the Visual Chinese Grammatical Error Correction[code]
2025Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction[code]
2026Improving Proficiency and Grammar Accuracy for Chinese Language Learners with Large Language Models

Czech

Keywords / OverviewYearPaperNote
AKCES-GEC dataset2019Grammatical Error Correction in Low-Resource Scenarios[data]
Grammar Error Correction Corpus for Czech (GECCC)2022Czech Grammar Error Correction with a Large and Diverse Corpus[data]

Estonian

Keywords / OverviewYearPaperNote
2025Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian[data]

Finnish

Keywords / OverviewYearPaperNote
2024Correcting Challenging Finnish Learner Texts With Claude, GPT-3.5 and GPT-4 Large Language Models

Geek

Keywords / OverviewYearPaperNote
Greek Learner Corpus2018Stand-off annotation in learner corpora: compiling the Greek Learner Corpus (GLC)
ELERRANT2021ELERRANT: Automatic Grammatical Error Type Classification for Greek[code]

German

Keywords / OverviewYearPaperNote
Falko-MERLIN dataset2018Using Wikipedia Edits in Low Resource Grammatical Error Correction[data]

Gujarati

Keywords / OverviewYearPaperNote
2026Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory[data] [Gujarati ERRANT]

Indian

Keywords / OverviewYearPaperNote
2014Detection and correction of non word spelling errors in Hindi language
HiWikiEd dataset2020Generating Inflectional Errors for Grammatical Error Correction in Hindi[data]
Hi-GEC2025Hi-GEC: Hindi Grammar Error Correction in Low Resource Scenario[code]
IndiGEC2025IndiGEC: Multilingual Grammar Error Correction for Low-Resource Indian Languages[code]

Icelandic

Keywords / OverviewYearPaperNote
Byte-level approach2023Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora[code]

Japanese

Keywords / OverviewYearPaperNote
Character-level RNN-based seq2seq2018Automatic Error Correction on Japanese Functional Expressions Using Character-based Neural Machine Translation
Constructing retrieval system for Japanese GEC2019Grammatical-Error-Aware Incorrect Example Retrieval System for Learners of Japanese as a Second Language
TMU Evaluation Corpus for Japanese Learners2020Construction of an Evaluation Corpus for Grammatical Error Correction for Learners of Japanese as a Second Language[data: Fill this form]
Non-Autoregressive approach2020Non-Autoregressive Grammatical Error Correction Toward a Writing Support System
2022Construction of a Quality Estimation Dataset for Automatic Evaluation of Japanese Grammatical Error Correction

Korean

Keywords / OverviewYearPaperNote
KAGAS2023Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation[code] [data request form]
2024Search if you don’t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models
2025Unified Automated Essay Scoring and Grammatical Error Correction

Lithuanian

Keywords / OverviewYearPaperNote
2022Towards Lithuanian grammatical error correction[code]

Romain

Keywords / OverviewYearPaperNote
2020Neural Grammatical Error Correction for Romanian[code]

Russian

Keywords / OverviewYearPaperNote
RULEC-GEC dataset2019Grammar Error Correction in Morphologically Rich Languages: The Case of Russian[data]
RU-Lang8 dataset2021New Dataset and Strong Baselines for the Grammatical Error Correction of Russian[data]
Additional annotations for RULEC and RU-Lang82024Multi-Reference Benchmarks for Russian Grammatical Error Correction[RULEC] [RU-Lang8]
2024Universal Dependencies for Learner Russian[code]
2025Grammatical Error Correction via Sequence Tagging for Russian[code]
LORuGEC2025LLMs in alliance with Edit-based models: advancing In-Context Learning for Grammatical Error Correction by Specific Example Selection[data] [code]

Spanish

Keywords / OverviewYearPaperNote
COWS-L2H2020Developing NLP Tools with a New Corpus of Learner Spanish[data]

Swedish

Keywords / OverviewYearPaperNote
2024Evaluation of Really Good Grammatical Error Correctioncode

Turkish

Keywords / OverviewYearPaperNote
ERRANT-TR2023Towards Automatic Grammatical Error Type Classification for Turkish[code]
GECTurk WEB2025GECTurk WEB: An Explainable Online Platform for Turkish Grammatical Error Detection and Correction[website]

Ukrainian

Keywords / OverviewYearPaperNote
UA-GEC2023UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language[data]
UNLP 2023 Shared Task2023The UNLP 2023 Shared Task on Grammatical Error Correction for Ukrainian
2023Comparative Study of Models Trained on Synthetic Data for Ukrainian Grammatical Error CorrectionUNLP-2023: Pravopysnyk
2023A Low-Resource Approach to the Grammatical Error Correction of UkrainianUNLP-2023: QC-NLP
2023RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to SpansUNLP-2023: WebSpellChecker

Zarma

Keywords / OverviewYearPaperNote
2026Grammatical Error Correction for Low-Resource Languages: The Case of Zarma[Data]

Contributors

gotutiyan

82 commits

Silviase

2 commits

xiaoouwang

1 commits

Similar repos

gotutiyan/gec-metrics

A library for evaluation of Grammatical Error Correction (GEC). Accepted to ACL'25 Demo:…

14

same org

gotutiyan/IMPARA

UNOFFICIAL implementation of "IMPARA: Impact-Based Metric for GEC Using Parallel Data", COLING2022

2

same org

destwang/CTCResources

269

nghuyong/Chinese-text-correction-papers

text correction papers

316

naist-nlp/IMPARA-GED

Model

IMPARA-GED

0

TW-NLP/ChineseErrorCorrector

一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，文本纠错新Sota。（ 2026 ACL Main Oral ）

647

wangwang110/CSC

ChineseBert用于中文拼写纠错

43

shibing624/pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在…

6,527

gotutiyan/GEC-Info

Repository to collect and categorize Grammatical Error Correction papers.

127

85 commits

updated Aug 16, 2026

See the code

README

GEC Information

Policy

  • This repository aims to collect and categorize GEC (Grammatical Error Correction) papers.
  • Unlike NLP-progress, GEC-Info does not consider performance on benchmarks.
    • Authors and conferences are also not be considered.
  • The papers are limited to refereed papers in international conferences for now.
    • This is not the case for survey papers.

Contributing

  • Pull Requests for adding papers are accepted. Please make a commit changing only lines regarding the addition of papers (and take care of changing by auto-formatting).
  • You can also request to add papers as an issue.

It can also be viewed on GitHub Pages

Overview

Surveys

TitleYearPageNote
"Automated Grammatical Error Correction: A Comprehensive Review"2017[paper]
"A Comprehensive Survey of Grammar Error Correction"2020[paper]
"Recent Trends in the Use of Deep Learning Models for Grammar Error Handling"2020[paper]
"Grammatical Error Correction: A Survey of the State of the Art"2022[paper]

Shared Tasks

NameYearPaperNote
HOO 20112011[paper][website]
HOO 20122012[paper][website]
CoNLL-20132013[paper][website]
CoNLL-20142014[paper][website] [system outputs]
BEA-20192019[paper][website] [system outpus]
BHASHA 20252025Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025Indian Languages. Teams: [Niyamika] [Horizon] [A3-108] [DLRG] [akhilrajeevp]

Libraries

NameYearPaperNote
UnifiedGEC2025UnifiedGEC: Integrating Grammatical Error Correction Approaches for Multi-languages with a Unified Framework[code]
gec-metrics2025gec-metrics: A Unified Library for Grammatical Error Correction Evaluation[code]

Datasets

For Training (Real Data)

NameYearPaperNote
EFCamDat2014Automatic Linguistic Annotation ofLarge Scale L2 Databases: The EF-Cambridge Open Language Database(EFCamDat) The EF Cambridge Open Language Database (efcamdat) Information for Users[download v2]
GitHub Typo Corpus2019GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors[download]
W&I+LOCNESS on BEA2019 Shared Task2019Developing an Automated Writing Placement System for ESL Learners [direct download]
FCE2011A New Dataset and Method for Automatically Grading ESOL Texts[direct download]
NUCLE2013Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English[download]
ICNALE2013The ICNALE and Sophisticated Contrastive Interlanguage Analysis of Asian Learners of English[download]
Lang-82011Mining Revision Log of Language Learning SNS for Automated Japanese Error Correction of Second Language Learners[website] [download: Fill this form]
Related tools are useful. See the [Other Tools] for the details.

For Training (Pseudo/Systhetic Data)

NameYearPaperNote
PIE-synthetic2019Parallel Iterative Edit Models for Local Sequence Transduction[download]
OmniGEC2025Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction[HF datasets], [code]. Czech, English, Estonian, German, Greek, Icelandic, Italian, Latvian, Slovene, Swedish, and Ukrainian

For Evaluation

NameYearPaperNote
KJ2011Creating a manually error-tagged and shallow-parsed learner corpus[download]
CoNLL-20132013The CoNLL-2013 Shared Task on Grammatical Error Correction[direct download]
CoNLL-20142014The CoNLL-2014 Shared Task on Grammatical Error Correction[direct download]
10 additional annotations for the CoNLL142015How Far are We from Fully Automatic High Quality Grammatical Error Correction?[direct download]
8 additional annotations for the CoNLL142016Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality[download]
JFLEG2017JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction[download]
GMEG-Data2019Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses[code]
CWEB2020Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses[download]
ErAConD2021ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction[data]
Training dataset is also included.
RobustGEC2023RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation[code]
CSW Lang-8 Dataset2024Grammatical Error Correction for Code-Switched Sentences by Learners of English[code/data]
CTSEG2025Targeted Syntactic Evaluation for Grammatical Error Correction[data]

Performance measures

Reference-based

NameYearPaperNote
M^2 Scorer2012Better Evaluation for Grammatical Error Correction[code]
It is often used to evaluate CoNLL-2013 and CoNLL-2014.
GLEU2015Ground Truth for Grammatical Error Correction Metrics
GLEU Without Tuning		[code]
It is often used to evaluate JFLEG.
I-measure2015Towards a standard evaluation method for grammatical error detection and correction[code]
Code is available only python 2.x.
ERRANT2016Automatic Extraction of Learner Errors in ESL Sentences Using Linguistically Enhanced Alignments
Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction		[code]
It is often used to evaluate BEA-2019.
GMEG-Metric2019Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses[code]
Ridge regression using existing metrics (e.g. ERRANT, GLEU) as features.
GoToScorer2019Taking the Correction Difficulty into Account in Grammatical Error Correction Evaluation[code]
It can be evaluated systems considering error correction difficulty.
PT-M22022Revisiting Grammatical Error Correction Evaluation and Beyond[code]
CLEME2023CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction[code]
GREEN2024n-gram F-score for Evaluating Grammatical Error Correction[code]
2025Refined Evaluation for End-to-End Grammatical Error Correction Using an Alignment-Based Approach[website]
CLEME2.02025CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction[code]
ERRANT extended to multiple languages2025Multilingual Grammatical Error Annotation: Combining Language-Agnostic Framework with Language-Specific Flexibility[code]

Reference-free

Keywords / OverviewYearPaperNote
Scoring by counting the errors2016There’s No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction[code]
Fluency + grammaticality + meaning preservation2017Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems
USim2018Reference-less Measure of Faithfulness for Grammatical Error Correction[code]
SOME2020SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction[code]
Scribendi Score2021Is this the end of the gold standard? A straightforward reference-less grammatical error correction metric[Unofficial code]
IMPARA2022IMPARA: Impact-Based Metric for GEC Using Parallel Data[code]
2024Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction
IMPARA-GED2025IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator[Official model]
2025LLM-based post-editing as reference-free GEC evaluation

Meta-evaluation

Keywords / OverviewYearPaperNote
Re-rank the CoNLL14 systems by human evaluation2015Human Evaluation of Grammatical Error Correction Systems[code]
Reassess M^2, I-measure, GLEU by comparing human evaluation2018A Reassessment of Reference-Based Grammatical Error Correction Metrics[code]
MAEGE2018Automatic Metric Validation for Grammatical Error Correction[code]
SEEDA2024Revisiting Meta-evaluation for Grammatical Error Correction[code]

Quality Estimation

Keywords / OverviewYearPaperNote
2022ProQE: Proficiency-wise Quality Estimation dataset for Grammatical Error Correction

Models

Before Neural (E.g., SMT)

Keywords / OverviewYearPaperNote
2006Correcting ESL Errors Using Phrasal SMT Techniques
2009Using First and Second Language Models to Correct Preposition Errors in Second Language Authoring
2010Generating Confusion Sets for Context-Sensitive Error Correction
2011Correcting Semantic Collocation Errors with L1-induced Paraphrases
2012Tense and Aspect Error Correction for ESL Learners Using Global Context
2012Exploring Grammatical Error Correction with Not-So-Crummy Machine Translation
2014Grammatical error correction using hybrid systems and type filteringCoNLL2014: CAMB
2014The AMU System in the CoNLL-2014 Shared Task: Grammatical Error Correction by Data-Intensive and Feature-Rich Statistical Machine TranslationCoNLL2014: AMU
2014The Illinois-Columbia System in the CoNLL-2014 Shared TaskCoNLL2014: CUUI
2014RACAI GEC – A hybrid approach to Grammatical Error CorrectionCoNLL2014: RAC
2014Grammatical Error Detection Using Tagger DisagreementCoNLL2014: UFC
2014CoNLL 2014 Shared Task: Grammatical Error Correction with a Syntactic N-gram Language Model from a Big CorporaCoNLL2014: IPN
2014Tuning a Grammar Correction System for Increased PrecisionCoNLL2014: IITB
2014POSTECH Grammatical Error Correction System in the CoNLL-2014 Shared TaskCoNLL2014: POST
2014Grammatical Error Detection and Correction using a Single Maximum Entropy ModelCoNLL2014: SJTU
2014Factored Statistical Machine Translation for Grammatical Error CorrectionCoNLL2014: UMC
2014NTHU at the CoNLL-2014 Shared TaskCoNLL2014: NTHU
2014A Unified Framework for Grammar Error CorrectionCoNLL2014: PKU
2016Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction
2016Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models
Phrase-based SMT2016Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction[code]
Word-level SMT enhanced NNJMs + char-based SMT2017Connecting the Dots: Towards Human-Level Grammatical Error Correction[code]
SMEG2017Systematically Adapting Machine Translation for Grammatical Error Correction[code]

Encoder-Decoder

Keywords / OverviewYearPaperNote
First NMT-based approach2016Grammatical error correction using neural machine translation
2016Neural Network Translation Models for Grammatical Error Correction
Neural reinforcement learning2017Grammatical Error Correction with Neural Reinforcement Learning[code]
A nested attention (word and char attention)2017A Nested Attention Neural Hybrid Model for Grammatical Error Correction
Re-ranking N-best sentence (by SMT) with LSTM-based GED2017Neural Sequence-Labelling Models for Grammatical Error Correction
Hybrid SMT and NMT2018Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
CNN-based Encder-Decoder approach2018A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction[code]
Fluency boosting learning2018Fluency Boost Learning and Inference for Neural Grammatical Error Correction[code] [arXiv]
Copy-Augmented Architecture2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data[code]
Consider a few previous sentences2019Cross-Sentence Grammatical Error Correction[code]
Use sentence-level error dectection2019The AIP-Tohoku System at the BEA-2019 Shared TaskBEA-2019: AIP-Tohoku
Four CNN + eight Transformer2019The LAIX Systems in the BEA-2019 GEC Shared TaskBEA-2019: LAIX
Combine Transformer+CNN with FST + Re-ranking2019Neural and FST-based approaches to grammatical error correctionBEA-2019: CAMB-CLED
Transformer seq2seq + BERT re-ranker2019TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted TrackBEA-2019: TMU
Apply noisy channel with BERT and GPT-2 as LM2019Noisy Channel for Low Resource Grammatical Error CorrectionBEA-2019: Siteimprove
Use Finite State Transducers2019Neural Grammatical Error Correction with Finite State Transducers
BERT-fuse2020Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction[code]
Adversarial approach (G:seq2seq D:sentence-pair classification)2020Adversarial Grammatical Error Correction
Erroneous span correction and detection2020Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
Document-level approach2020Document-level grammatical error correction[code]
Beam search considering copy probability2020Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction
BART-based2020Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model[code]
VERNet2021Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction[code]
Shallow Aggressive Decoding2021Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding[code]
T5-based2021A Simple Recipe for Multilingual Grammatical Error Correction[code]
Use multiclass GED for Transformer seq2seq and reranking2021Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems
GEC for writing improvement model adapted to the writer’s L12021Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models[code]
Constrastive Leaning approach2021Grammatical Error Correction with Contrastive Learning in Low Error Density Domains[code]
Sequence Span Rewriting2021Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
Pretrain by DAE + sequential transfer learning2019A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning[code]
BEA-2019: Kakao&Brain
Dependent Self-Attention (DSA)2021Grammatical Error Correction with Dependency Distance
A GEC model using only 11.6MB2021An efficient system for grammatical error correction on mobile devices
LM-Critic2021LM-Critic: Language Models for Unsupervised Grammatical Error Correction[code]
Supervised setting is also performed
2022Interpretability for Language Learners Using Example-Based Grammatical Error Correction[code]
2022Position Offset Label Prediction for Grammatical Error Correction
SynGEC2022SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser[code]
EdiT52022EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start[code]
GEC-DePenD2023GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding[code]
TemplateGEC2023TemplateGEC: Improving Grammatical Error Correction with Detection Template[code]
LET2023LET: Leveraging Error Type Information for Grammatical Error Correction
2023Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction
Use speech information2023Improving Grammatical Error Correction with Multimodal Feature Integration[code]
2023Improving Autoregressive Grammatical Error Correction with Non-autoregressive Models
2023Unsupervised Grammatical Error Correction Rivaling Supervised Methods[code]
2024No Error Left Behind: Multilingual Grammatical Error Correction with Pre-trained Translation Models
EDU Copy Mechanism2024Improving Copy-oriented Text Generation via EDU Copy Mechanism
2024Efficient and Interpretable Grammatical Error Correction with Mixture of Experts[code]
2025InstructGEC: Enhancing Unsupervised Grammatical Error Correction with Instruction Tuning
CxGGEC2025CxGGEC: Construction-Guided Grammatical Error Correction

Tagging / Non-autogressive

Keywords / OverviewYearPaperNote
LSTM tagger for word coice task2019Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems[code]
PIE2019Parallel Iterative Edit Models for Local Sequence Transduction[code]
LaserTagger2019Encode, Tag, Realize: High-Precision Text Editing[code]
GECToR2020GECToR – Grammatical Error Correction: Tag, Not Rewrite[code]
Seq2Edits2020Seq2Edits: Sequence Transduction Using Span-level Edit Operations[code]
GAN-like sequence labeling2021Grammatical Error Correction as GAN-like Sequence Labeling
GECToR Large2022Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction[code] [Author's Master Thesis]
2021Efficient Grammatical Error Correction with Hierarchical Error Detections and Correction[code]
2022Type-Driven Multi-Turn Corrections for Grammatical Error Correction[code]
2023An Extended Sequence Tagging Vocabulary for Grammatical Error Correction[code]

Large Language Model

Keywords / OverviewYearPaperNote
5-gram LM based approach2018Language Model Based Grammatical Error Correction without Annotated Training Data[code]
Use Finite State Transducers2019Neural Grammatical Error Correction with Finite State Transducers
Use LM (BERT, GPT-1,2)2019The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction
2023Reducing Sequence Length by Predicting Edit Spans with Large Language Models
2023Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods
2024Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency
2024GPT-3.5 for Grammatical Error CorrectionTarget languages: CZ, DE, EN, RU, SV, UA
2024Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction[code]
mEdIT2024mEdIT: Multilingual Text Editing via Instruction Tuning[code]
DeCoGLM2024Detection-Correction Structure via General Language Model for Grammatical Error Correction[code]
For code-switched text2024LLM-based Code-Switched Text Generation for Grammatical Error Correction[code]
EPO2025Edit-Wise Preference Optimization for Grammatical Error Correction
2024Prompting open-source and commercial language models for grammatical error correction of English learner text[code]
2025Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction[code]
2025Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction[code]
2025Adapting LLMs for Minimal-edit Grammatical Error Correction[code]
2025Leveraging What’s Overfixed: Post-Correction via LLM Grammatical Error Overcorrection

Ensembles / Post-processing

Keywords / OverviewYearPaperNote
Use MENT2014System Combination for Grammatical Error Correction
2016Grammatical Error Correction: Machine Translation and Classifiers
2019Learning to combine Grammatical Error Corrections[code]
Diversity-Driven Combination (DDC)2021Diversity-Driven Combination for Grammatical Error Correction[code]
Select a system for each error type with IP2021System Combination for Grammatical Error Correction Based on Integer Programming[code]
2022Frustratingly Easy System Combination for Grammatical Error Correction[code]
EditScorer2022Improved grammatical error correction by ranking elementary edits[code]
GRECO2023System Combination via Quality Estimation for Grammatical Error Correction[code]
2024Improving Grammatical Error Correction by Correction Acceptability Discrimination

Strategies

This includes methods such as decoding techniques and approaches that modify the loss function while keeping the model architecture unchanged.

Keywords / OverviewYearPaperNote
2012A Beam-Search Decoder for Grammatical Error Correction
2016Discriminative Reranking for Grammatical Error Correction with Statistical Machine Translation
2016Candidate re-ranking for SMT-based grammatical error correction
Some methods that can be adapted neural MT2018Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task[code]
Iterative decoding2018Weakly Supervised Grammatical Error Correction using Iterative Decoding
2019Controlling Grammatical Error Correction Using Word Edit Rate
Add adversarial examples continually2020Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples
Cross-lingual Transfer Learning2020Cross-lingual Transfer Learning for Grammatical Error Correction
Data Weighted Training Strategies2020Data Weighted Training Strategies for Grammatical Error Correction
Align-and-Predict Decoding2022Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error Correction[code]
2023Mitigating Exposure Bias in Grammatical Error Correction with Data Augmentation and Reweighting[code]
BTR2023Bidirectional Transformer Reranker for Grammatical Error Correction[code]
2023Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule
MainGEC2023Grammatical Error Correction via Mixed-Grained Weighted Training
2023Improving Seq2Seq Grammatical Error Correction via Decoding Interventions[code]
2024Multi-pass Decoding for Grammatical Error Correction

Data Augmentation

Keywords / OverviewYearPaperNote
Make artificial errors in a probabilistic manner2014Generating artificial errors for grammatical error correction
Back translation2016Improving Neural Machine Translation Models with Monolingual Data
SMT based MT + pattern extraction2017Artificial Error Generation with Machine Translation and Syntactic Patterns
Diverse back translation with noisy beam search2018Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction
MAGEC2019Minimally-Augmented Grammatical Error CorrectionSupervised setting is also performed
DirectNoise2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled DataThe method was first called "DirectNoise" by [kiyono+ 2019]?
Substituting words using confusion sets2019Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data[synthetic data]
BEA-2019: UEDIN-MS
Error+Context Dictionary2019Improving Precision of Grammatical Error Correction with a Cheat SheetBEA-2019: Buffalo
Use Google Translate for making pseudo data2019(Almost) Unsupervised Grammatical Error Correction using a Synthetic Comparable CorpusBEA-2019: TMU in Low Resource
Inverted Spellchecker + Patterns+POS2019A Comparative Study of Synthetic Data Generation Methods for Grammatical Error Correction
Methods for erroneous data generation2019Erroneous data generation for Grammatical Error CorrectionBEA-2019: Shuyao
Wikipedia revision & Wikipedia round-trip translation2019Corpora Generation for Grammatical Error Correction
Create confusion sets by edit distance, word embeddings, spell-breaking2019Minimally-Augmented Grammatical Error CorrectionSupervised setting is also performed
Explore methods to make pseude data, seed corpus, training settings2019An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction[code]
2020Massive Exploration of Pseudo Data for Grammatical Error Correction
Control error rates and error types by rule-based corruption and filtered back-translation2020Controllable Data Synthesis Method for Grammatical Error Correction
Use machine translation pairs2020Improving Grammatical Error Correction with Machine Translation Pairs
Edit latent representation2020Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation
Consider learner’s error tendency2020Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency
Tagged corruption2021Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models[code]
Use 188 modules2021Various Errors Improve Neural Grammatical Error Correction[code]
Use real error petterns and linguistic knowledge2021Data Augmentation of Incorporating Real Error Patterns and Linguistic Knowledge for Grammatical Error Correction
Divide non-English sentence into chunks → translate to English for each of them → concatenate2021Grammatical Error Generation Based on Translated Fragments
2023Grammatical Error Correction through Round-Trip Machine Translation
TransGEC2023TransGEC: Improving Grammatical Error Correction with Translationese[code]
Focus on gender bias2023Gender-Inclusive Grammatical Error Correction through Augmentation[code]
2023Training for Grammatical Error Correction Without Human-Annotated L2 Learners’ Corpora
MixEdit2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction[code]
2024Synthetic Data Generation for Low-resource Grammatical Error Correction with Tagged Corruption Models
2024Improving Grammatical Error Correction via Contextual Data Augmentation[code]
2024To Err Is Human, but Llamas Can Learn It Too[code]
2025Large Language Models are Good Annotators for Type-aware Data Augmentation in Grammatical Error Correction[code]
2025Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages
2025Low-Resource Grammatical Error Correction: Selective Data Augmentation with Round-Trip Machine Translation[code]. experiments Include Russian and Ukrainian.

Data Cleaning

Keywords / OverviewYearPaperNote
A Self-Refinement Strategy for Noise Reduction2020A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction
cLang8 (Cleaned Lang-8)2021A Simple Recipe for Multilingual Grammatical Error Correction[code]

Analyses

Keywords / OverviewYearPaperNote
2011Algorithm Selection and Model Adaptation for ESL Correction Tasks
2012The Effect of Learner Corpus Size in Grammatical Error Correction of ESL Writings
2015How Far are We from Fully Automatic High Quality Grammatical Error Correction?
Human annotation focused on fluency2016Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality[code]
2017GEC into the future: Where are we going and how do we get there?
2018Inherent Biases in Reference-based Evaluation for Grammatical Error Correction[code]
2018Assessing Grammatical Correctness in Language Learning
Quality estimation (and re-ranking using estimated score)2018Neural Quality Estimation of Grammatical Error Correction[code]
Evaluate four systems (SMT, CNN, LSTM, Transformer) for six corpora (CoNLL13&14, FCE, JFLEG, KJ, ICNALE)2019Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models — Is Single-Corpus Evaluation Enough?
Compare CNN, Transformer, PRPN, ON-LSTM as back-translation models2019The Unbearable Weight of Generating Artificial Errors for Grammatical Error Correction
GEC for post-processing2019Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
CGOP2020Comparison of the Evaluation Metrics for Neural Grammatical Error Correction With OvercorrectionMetric Considering overcorrection
Create new gold data by post-editing system outputs2021How Good (really) are Grammatical Error Correction Systems?
Explore whether models have grammatical knowledge with Known-setting and Unknown-setting2021Do Grammatical Error Correction Models Realize Grammatical Generalization?
Compare CNN, LSTM, transformer or combinations of them as BT models2021Comparison of Grammatical Error Correction Using Back-Translation Models
2022Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
2022Grammatical Error Correction: Are We There Yet?
2022Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?[code]
2023ChatBack: Investigating Methods of Providing Grammatical Error Feedback in a GUI-based Language Learning Chatbot
2023A Closer Look at k-Nearest Neighbors Grammatical Error Correction
2023Grammatical Error Correction for Sentence-level Assessment in Language Learning
2023Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
2024Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models][code]
2024Likelihood-based Mitigation of Evaluation Bias in Large Language Models
2025Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?[code]
2025Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction[code]
2025Reliability Crisis of Reference-free Metrics for Grammatical Error Correction[code]

Spoken Domain

Keywords / OverviewYearPaperNote
2019AUTOMATIC GRAMMATICAL ERROR DETECTION OF NON-NATIVE SPOKEN LEARNER ENGLISH
2020Grammatical error detection in transcriptions of spoken English
Disfluency detection (DD) model2020Spoken Language ‘Grammatical Error Correction’
2022On Assessing and Developing Spoken ’Grammatical Error Correction’ Systems

Applications

NameYearPaperNote
GECko++GECko+: a Grammatical and Discourse Error Correction Tool[website] [code]
An English assiting tool. Correction grammatical error and re-ordering sentences automatically.
MiSS2021MiSS: An Assistant for Multi-Style Simultaneous Translation[website] [demo video]
ALLECS2023ALLECS: A Lightweight Language Error Correction System[website] [code]
2023Doolittle: Benchmarks and Corpora for Academic Writing Formalization[code]
2025Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore[code]

Projects

NameWebsite
GramFormer[GitHub]

Other Tools

NameCodeNote
Lang8-NAIST-extractor[code]Scripts for extracting error-correct pairs from the Lang-8 Corpus.
M2Converter[code]Scripts for converting m2 file into source file and target file.
EFCamDat-Preprocess[code]

Other materials

NamePaperNote
NLP-progresswebsite
The performance ranking on some datasets.
A Crash Course in Automatic Grammatical Error Correction[paper]materials
The tutorial about GEC in COLING2020.
Chunngai/gec-papersgithub

Related Tasks

Grammatical Error Detection

Keywords / OverviewYearPaperNote
2003Automatic Error Detection in the Japanese Learners’ English Spoken Data
2006Detecting errors in English article usage by non-native speakers
2008The Ups and Downs of Preposition Error Detection in ESL Writing
2010Evaluating performance of grammatical error detection to maximize learning effect
A weighted measure according to crowdsourcing results (for GED)2011They Can Help: Using Crowdsourcing to Improve the Evaluation of Grammatical Error Detection Systems
2014Detecting Learner Errors in the Choice of Content Words Using Compositional Distributional Semantics
2016Compositional Sequence Labeling Models for Error Detection in Learner Writing
2017Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings[code]
2018Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection[code]
Bi-LSTM with contextual word embeddings2019Context is Key: Grammatical Error Detection with Contextual Word Representations
Multi-head and multi-layer attention2019Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection
2021Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical Errors
2022Probing for targeted syntactic knowledge through grammatical error detection[code]
2024Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection[data]
2025Oddballness: universal anomaly detection with language models[code]

Feedback Comment Generation

Keywords / OverviewYearPaperNote
2014Correcting Preposition Errors in Learner English Using Error Case Frames and Feedback Messages
English grammar checker with feedback in Japanese2018Grammatical Error Checker for Japanese Learners of EnglishThis is not a research as a feedback comment generation, but I classify it here for now
2019Toward a Task of Feedback Comment Generation for Writing Learning
2020Creating Corpora for Research in Feedback Comment Generation
2021Shared Task on Feedback Comment Generation for Language Learners
2023Template-guided Grammatical Error Feedback Comment Generation

Explainable Grammatical Error Correction

  • Studies to explain the reasons for and intentions of error correction.
Keywords / OverviewYearPaperNote
EXPECT2023Enhancing Grammatical Error Correction Systems with Explanations[code]
XGEC dataset2024Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction[data]
GEE2024GEE! Grammar Error Explanation with Large Language Models[code]

Document-level Revision

Keywords / OverviewYearPaperNote
TETRA2024Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond[code]

Other Languages

Arabic

Keywords / OverviewYearPaperNote
Arabic Learner Corpus2013Arabic Learner Corpus v1: A New Resource for Arabic Language Research[website]
QALB2014Large Scale Arabic Error Annotation: Guidelines and Framework[QALB Project Website]
QALB 2014 Shared Task2014The First QALB Shared Task on Automatic Text Correction for Arabic[website]
QALB 2015 Shared Task2015The Second QALB Shared Task on Automatic Text Correction for Arabic
ARETA2021Automatic Error Type Annotation for Arabic[code]
2023Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation[code]
2023Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction
2025ARWI: Arabic Write and Improve[website]
2025Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study[code]
Nahw2026Nahw: A Comprehensive Benchmark of Arabic Grammar Understanding, Error Detection, Correction, and Explanation[Data]

Bangla

Keywords / OverviewYearPaperNote
2021Development of Bangla Spell and Grammar Checkers: Resource Creation and Evaluation
2025Leveraging LLMs for Bangla Grammar Error Correction: Error Categorization, Synthetic Data, and Model Evaluation[code]

Chinese

Keywords / OverviewYearPaperNote
2013Chinese Spelling Checker Based on Statistical Machine Translation
2014Chinese Word Ordering Errors Detection and Correction for Non-Native Chinese Language Learners
2015Improving Chinese Grammatical Error Correction with Corpus Augmentation and Hierarchical Phrase-based Statistical Machine Translation
NLPCC-2018 Shared Task2018Overview of the NLPCC 2018 Shared Task: Grammatical Error Correction[data]
Two-stage: Spell checker → seq2seq2019A Two-Stage Model for Chinese Grammatical Error Correction
CNN-based seq2seq2019Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model
MaskGEC2020MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking
2020Chinese Grammatical Error Detection Based on BERT Model
2020BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis
2020Heterogeneous Recycle Generation for Chinese Grammatical Error Correction
NLPTEA-2020 Shared Task2020Overview of NLPTEA-2020 Shared Task for Chinese Grammatical Error Diagnosis
Tail-to-Tail Non-Autoregressive Sequence Prediction2021Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
2021"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction
2022Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students
2022MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction[code]
2022Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error Generation[code]
2022String Editing Based Chinese Grammatical Error Diagnosis
CLG2022Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction[code]
2022From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction
FCGEC2022FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction[code]
2023Are Pre-trained Language Models Useful for Model Ensemble in Chinese Grammatical Error Correction?[code]
2023Focal Training and Tagger Decouple for Grammatical Error Correction
NaSGEC2023NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts[code]
TLM2023TLM: Token-Level Masking for Transformers[code]
2024LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction[code]
Alirector2024Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector[code]
2024Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction[code]
2024Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method[code]
2025Improving Automatic Grammatical Error Annotation for Chinese Through Linguistically-Informed Error Typology[website]
2025A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction[code]
VisCGEC2025VisCGEC: Benchmarking the Visual Chinese Grammatical Error Correction[code]
2025Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction[code]
2026Improving Proficiency and Grammar Accuracy for Chinese Language Learners with Large Language Models

Czech

Keywords / OverviewYearPaperNote
AKCES-GEC dataset2019Grammatical Error Correction in Low-Resource Scenarios[data]
Grammar Error Correction Corpus for Czech (GECCC)2022Czech Grammar Error Correction with a Large and Diverse Corpus[data]

Estonian

Keywords / OverviewYearPaperNote
2025Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian[data]

Finnish

Keywords / OverviewYearPaperNote
2024Correcting Challenging Finnish Learner Texts With Claude, GPT-3.5 and GPT-4 Large Language Models

Geek

Keywords / OverviewYearPaperNote
Greek Learner Corpus2018Stand-off annotation in learner corpora: compiling the Greek Learner Corpus (GLC)
ELERRANT2021ELERRANT: Automatic Grammatical Error Type Classification for Greek[code]

German

Keywords / OverviewYearPaperNote
Falko-MERLIN dataset2018Using Wikipedia Edits in Low Resource Grammatical Error Correction[data]

Gujarati

Keywords / OverviewYearPaperNote
2026Smruti: Grammatical Error Correction for Gujarati using LLMs with Non-Parametric Memory[data] [Gujarati ERRANT]

Indian

Keywords / OverviewYearPaperNote
2014Detection and correction of non word spelling errors in Hindi language
HiWikiEd dataset2020Generating Inflectional Errors for Grammatical Error Correction in Hindi[data]
Hi-GEC2025Hi-GEC: Hindi Grammar Error Correction in Low Resource Scenario[code]
IndiGEC2025IndiGEC: Multilingual Grammar Error Correction for Low-Resource Indian Languages[code]

Icelandic

Keywords / OverviewYearPaperNote
Byte-level approach2023Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora[code]

Japanese

Keywords / OverviewYearPaperNote
Character-level RNN-based seq2seq2018Automatic Error Correction on Japanese Functional Expressions Using Character-based Neural Machine Translation
Constructing retrieval system for Japanese GEC2019Grammatical-Error-Aware Incorrect Example Retrieval System for Learners of Japanese as a Second Language
TMU Evaluation Corpus for Japanese Learners2020Construction of an Evaluation Corpus for Grammatical Error Correction for Learners of Japanese as a Second Language[data: Fill this form]
Non-Autoregressive approach2020Non-Autoregressive Grammatical Error Correction Toward a Writing Support System
2022Construction of a Quality Estimation Dataset for Automatic Evaluation of Japanese Grammatical Error Correction

Korean

Keywords / OverviewYearPaperNote
KAGAS2023Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation[code] [data request form]
2024Search if you don’t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models
2025Unified Automated Essay Scoring and Grammatical Error Correction

Lithuanian

Keywords / OverviewYearPaperNote
2022Towards Lithuanian grammatical error correction[code]

Romain

Keywords / OverviewYearPaperNote
2020Neural Grammatical Error Correction for Romanian[code]

Russian

Keywords / OverviewYearPaperNote
RULEC-GEC dataset2019Grammar Error Correction in Morphologically Rich Languages: The Case of Russian[data]
RU-Lang8 dataset2021New Dataset and Strong Baselines for the Grammatical Error Correction of Russian[data]
Additional annotations for RULEC and RU-Lang82024Multi-Reference Benchmarks for Russian Grammatical Error Correction[RULEC] [RU-Lang8]
2024Universal Dependencies for Learner Russian[code]
2025Grammatical Error Correction via Sequence Tagging for Russian[code]
LORuGEC2025LLMs in alliance with Edit-based models: advancing In-Context Learning for Grammatical Error Correction by Specific Example Selection[data] [code]

Spanish

Keywords / OverviewYearPaperNote
COWS-L2H2020Developing NLP Tools with a New Corpus of Learner Spanish[data]

Swedish

Keywords / OverviewYearPaperNote
2024Evaluation of Really Good Grammatical Error Correctioncode

Turkish

Keywords / OverviewYearPaperNote
ERRANT-TR2023Towards Automatic Grammatical Error Type Classification for Turkish[code]
GECTurk WEB2025GECTurk WEB: An Explainable Online Platform for Turkish Grammatical Error Detection and Correction[website]

Ukrainian

Keywords / OverviewYearPaperNote
UA-GEC2023UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language[data]
UNLP 2023 Shared Task2023The UNLP 2023 Shared Task on Grammatical Error Correction for Ukrainian
2023Comparative Study of Models Trained on Synthetic Data for Ukrainian Grammatical Error CorrectionUNLP-2023: Pravopysnyk
2023A Low-Resource Approach to the Grammatical Error Correction of UkrainianUNLP-2023: QC-NLP
2023RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to SpansUNLP-2023: WebSpellChecker

Zarma

Keywords / OverviewYearPaperNote
2026Grammatical Error Correction for Low-Resource Languages: The Case of Zarma[Data]

Similar repos

gotutiyan/gec-metrics

A library for evaluation of Grammatical Error Correction (GEC). Accepted to ACL'25 Demo:…

14

same org

gotutiyan/IMPARA

UNOFFICIAL implementation of "IMPARA: Impact-Based Metric for GEC Using Parallel Data", COLING2022

2

same org

destwang/CTCResources

269

nghuyong/Chinese-text-correction-papers

text correction papers

316

naist-nlp/IMPARA-GED

Model

IMPARA-GED

0

TW-NLP/ChineseErrorCorrector

一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，文本纠错新Sota。（ 2026 ACL Main Oral ）

647

wangwang110/CSC

ChineseBert用于中文拼写纠错

43

shibing624/pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在…

6,527

Contributors

gotutiyan

82 commits

Silviase

2 commits

xiaoouwang

1 commits