SOTAVerified

Grammatical Error Correction

Grammatical Error Correction (GEC) is the task of correcting different kinds of errors in text such as spelling, punctuation, grammatical, and word choice errors.

GEC is typically formulated as a sentence correction task. A GEC system takes a potentially erroneous sentence as input and is expected to transform it to its corrected version. See the example given below:

| Input (Erroneous) | Output (Corrected) | | ------------------------- | ---------------------- | |She see Tom is catched by policeman in park at last night. | She saw Tom caught by a policeman in the park last night.|

Papers

Showing 351–400 of 415 papers

TitleStatusHype
Grammatical Error Correction in Low-Resource ScenariosCode0
Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical StudyCode0
Comparative study of models trained on synthetic data for Ukrainian grammatical error correctionCode0
Reassessing the Goals of Grammatical Error Correction: Fluency Instead of GrammaticalityCode0
RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to SpansCode0
TLM: Token-Level Masking for TransformersCode0
Type-Driven Multi-Turn Corrections for Grammatical Error CorrectionCode0
Classifying Syntactic Errors in Learner LanguageCode0
Grammatical Error Correction with Contrastive Learning in Low Error Density DomainsCode0
Multi-Class Grammatical Error Detection for Correction: A Tale of Two SystemsCode0
Multi-head Sequence Tagging Model for Grammatical Error CorrectionCode0
Reference-less Measure of Faithfulness for Grammatical Error CorrectionCode0
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-AugmentingCode0
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error CorrectionCode0
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder ModelsCode0
Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder modelsCode0
Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support SystemsCode0
Revisiting Meta-evaluation for Grammatical Error CorrectionCode0
Negative language transfer in learner English: A new datasetCode0
To Err Is Human, but Llamas Can Learn It TooCode0
Automatic Metric Validation for Grammatical Error CorrectionCode0
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic DataCode0
Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error CorrectionCode0
Neural Machine Translation Techniques for Named Entity TransliterationCode0
Neural Network Translation Models for Grammatical Error CorrectionCode0
Towards a standard evaluation method for grammatical error detection and correctionCode0
Neural Quality Estimation of Grammatical Error CorrectionCode0
IMPARA: Impact-Based Metric for GEC Using Parallel DataCode0
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence TasksCode0
Byte-Level Grammatical Error Correction Using Synthetic and Curated CorporaCode0
Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error CorrectionCode0
A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer LearningCode0
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation TaskCode0
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled DataCode0
Improving Grammatical Error Correction via Contextual Data AugmentationCode0
Improving Grammatical Error Correction with Machine Translation PairsCode0
Using Wikipedia Edits in Low Resource Grammatical Error CorrectionCode0
ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error CorrectionCode0
Seq2Edits: Sequence Transduction Using Span-level Edit OperationsCode0
Towards Lithuanian grammatical error correctionCode0
Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 DatasetCode0
Wronging a Right: Generating Better Errors to Improve Grammatical Error DetectionCode0
Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text SimplificationCode0
Inherent Biases in Reference-based Evaluation for Grammatical Error CorrectionCode0
Efficient and Interpretable Grammatical Error Correction with Mixture of ExpertsCode0
DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language ModelsCode0
Some Grammatical Errors are Frequent, Others are ImportantCode0
Is this the end of the gold standard? A straightforward reference-less grammatical error correction metricCode0
SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error CorrectionCode0
An Empirical Study of Incorporating Pseudo Data into Grammatical Error CorrectionCode0
Show:102550
← PrevPage 8 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Ensembles of best 7 models + GRECO + GTP-rerankF0.572.8—Unverified
2Majority-voting ensemble on best 7 modelsF0.571.8—Unverified
3GRECO (voting+ESC)F0.571.12—Unverified
4GEC-DI (LM+GED)F0.569.6—Unverified
5Unsupervised GEC + cLang8F0.569.6—Unverified
6ESCF0.569.51—Unverified
7T5F0.568.87—Unverified
8MoECEF0.567.79—Unverified
9SynGECF0.567.6—Unverified
10Sequence tagging + token-level transformations + two-stage fine-tuning (+BERT, RoBERTa, XLNet)F0.566.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Majority-voting ensemble on best 7 modelsF0.581.4—Unverified
2GRECO (voting+ESC)F0.580.84—Unverified
3ESCF0.579.9—Unverified
4RedPenNetF0.577.6—Unverified
5clang_large_ft2-gectorF0.577.1—Unverified
6Unsupervised GEC + cLang8F0.576.5—Unverified
7DeBERTa + RoBERTa + XLNetF0.576.05—Unverified
8MoECEF0.574.07—Unverified
9Sequence tagging + token-level transformations + two-stage fine-tuning (+RoBERTa, XLNet)F0.573.7—Unverified
10BEA CombinationF0.573.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Llama + 1M BT + goldF0.576.75—Unverified
2mT5-based multimodal MoEF0.576.3—Unverified
3gT5 xxlF0.575.96—Unverified
4TransformerF0.573.71—Unverified
5Transformer - synthetic pretrain onlyF0.551.41—Unverified
6Multilayer Convolutional Encoder-DecoderF0.543.35—Unverified
#ModelMetricClaimedVerifiedStatus
1VERNetGLEU62.1—Unverified
2Transformer + Pre-train with Pseudo Data + BERTGLEU62—Unverified
3SMT + BiGRUGLEU61.5—Unverified
4Copy-augmented Model (4 Ensemble +Denoising Autoencoder)GLEU61—Unverified
5TransformerGLEU59.9—Unverified
6CNN Seq2SeqGLEU57.47—Unverified
#ModelMetricClaimedVerifiedStatus
1Llama + 1M BT + goldF0.574.09—Unverified
2mBART-based model with synthetic dataF0.568.17—Unverified
3mT5 large + 10M synthF0.568.09—Unverified
4RedPenNetF0.567.71—Unverified
5ChatGPT (zero-shot)F0.527.4—Unverified
#ModelMetricClaimedVerifiedStatus
1GRECO (vote+ESC)F0.585.21—Unverified
2SMT + BiGRUF0.572.04—Unverified
3CNN Seq2SeqF0.570.14—Unverified
#ModelMetricClaimedVerifiedStatus
1CNN Seq2Seq + Quality EstimationF0.556.52—Unverified
2TransformerF0.555.8—Unverified
3+ BIFI with no criticF0.518.7—Unverified
#ModelMetricClaimedVerifiedStatus
1CNN Seq2Seq + Fluency Boost and inferenceGLEU62.37—Unverified
2CNN Seq2Seq + Fluency BoostF0.561.34—Unverified
3+ BIFI (ours)F0.542.4—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerGLEU59.9—Unverified
2CNN Seq2SeqGLEU57.47—Unverified
#ModelMetricClaimedVerifiedStatus
1Llama + 1M BT + goldF0.569.97—Unverified
#ModelMetricClaimedVerifiedStatus
1STG-Jointexact match34.1—Unverified
#ModelMetricClaimedVerifiedStatus
1GEC-DI (LM+GED)F0.548.61—Unverified
#ModelMetricClaimedVerifiedStatus
1RedPenNetF0.577.6—Unverified