Grammatical Error Correction

117 papers with code • 11 benchmarks • 15 datasets

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.

Libraries

Use these libraries to find Grammatical Error Correction models and implementations
2 papers
18,075

GEE! Grammar Error Explanation with Large Language Models

yixiao-song/gee-with-llms 16 Nov 2023

To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences.

0
16 Nov 2023

GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding

gibson210/gec-depend 14 Nov 2023

Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models.

1
14 Nov 2023

TLM: Token-Level Masking for Transformers

young1993/tlm 28 Oct 2023

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers.

5
28 Oct 2023

Improving Seq2Seq Grammatical Error Correction via Decoding Interventions

Jacob-Zhou/gecdi 23 Oct 2023

In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token.

27
23 Oct 2023

System Combination via Quality Estimation for Grammatical Error Correction

nusnlp/greco 23 Oct 2023

However, we found that existing GEC quality estimation models are not good enough in differentiating good corrections from bad ones, resulting in a low F0. 5 score when used for system combination.

6
23 Oct 2023

Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

zetangforward/csa-gec 20 Oct 2023

By leveraging the augmenting data from the GEC models themselves in the post-training process and introducing regularization data for cycle training, our proposed method can effectively improve the model robustness of well-trained GEC models with only a few more training epochs as an extra cost.

3
20 Oct 2023

Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

protagolabs/seq2seq_llm_evaluation 20 Oct 2023

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models.

1
20 Oct 2023

MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction

thukelab/mixedit 18 Oct 2023

In this paper, we aim to clarify how data augmentation improves GEC models.

5
18 Oct 2023

RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation

hillzhang1999/robustgec 11 Oct 2023

In this paper, we introduce RobustGEC, a benchmark designed to evaluate the context robustness of GEC systems.

13
11 Oct 2023

FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation

hydududu/flacgec 26 Sep 2023

Chinese Grammatical Error Correction (CGEC) has been attracting growing attention from researchers recently.

3
26 Sep 2023