CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction

• URL: http://arxiv.org/abs/2606.15069v1
• Date: Sat, 13 Jun 2026 02:58:13 GMT
• Title: CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction
• Abstract summary: Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks.<n>Existing GEC models usually fail to understand the error patterns in the varying contexts.<n>We propose CoCoGEC, a counterfactual generation framework that creates copies of training instances with error-irrelevant contexts altered.
• Score: 15.181557665760161
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates that the existing GEC models usually fail to understand the error patterns in the varying contexts. In this paper, we thoroughly investigate the counterfactuals for GEC tasks, where the subtle changes to the contexts could lead to the label flipping issue. We propose CoCoGEC, a counterfactual generation framework that creates copies of training instances with error-irrelevant contexts altered. Our framework systematically generates counterfactuals by (1) generating intra- and inter-sentence counterfactuals that maintain the error patterns as well as syntax of the original instances by altering the word-level and sentence-level contexts; (2) revising the generated counterfactuals by selecting the instances with flipped labels and high GEC Mutual Information (MI) coefficient. Extensive experiments show that our method substantially improves the stability of GEC models, outperforming a set of data augmentation baselines. Particularly, it could achieve absolute F0.5 gains of +9.9, +11.3, and +20.8 points on the perturbed BEA-19*,CoNLL-14*, and TEM-8* data set.Our code is released at https://github.com/Quinnok/CoCoGEC

Related papers

• Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation [73.9145653659403]
  We show that Generative Error Correction models struggle to generalize beyond the specific types of errors encountered during training. We propose DARAG, a novel approach designed to improve GEC for ASR in in-domain (ID) and OOD scenarios. Our approach is simple, scalable, and both domain- and language-agnostic.
  arXiv  Detail & Related papers  (2024-10-17T04:00:29Z)
• Improving Seq2Seq Grammatical Error Correction via Decoding Interventions [40.52259641181596]
  We propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally. We discover and investigate two types of critics: a pre-trained left-to-right language model critic and an incremental target-side grammatical error detector critic. Our framework consistently outperforms strong baselines and achieves results competitive with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-23T03:36:37Z)
• RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation [64.2568239429946]
  We introduce RobustGEC, a benchmark designed to evaluate the context robustness of GEC systems. We reveal that state-of-the-art GEC systems still lack sufficient robustness against context perturbations.
  arXiv  Detail & Related papers  (2023-10-11T08:33:23Z)
• CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction [32.44051877804761]
  Chunk-LEvel Multi-reference Evaluation (CLEME) is designed to evaluate Grammatical Error Correction (GEC) systems in the multi-reference evaluation setting. We conduct experiments on six English reference sets based on the CoNLL-2014 shared task.
  arXiv  Detail & Related papers  (2023-05-18T08:57:17Z)
• ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction [30.917993017459615]
  We present a novel parallel grammatical error correction (GEC) dataset drawn from open-domain conversations. This dataset is, to our knowledge, the first GEC dataset targeted to a conversational setting. To demonstrate the utility of the dataset, we use our annotated data to fine-tune a state-of-the-art GEC model.
  arXiv  Detail & Related papers  (2021-12-15T20:27:40Z)
• LM-Critic: Language Models for Unsupervised Grammatical Error Correction [128.9174409251852]
  We show how to leverage a pretrained language model (LM) in defining an LM-Critic, which judges a sentence to be grammatical. We apply this LM-Critic and BIFI along with a large set of unlabeled sentences to bootstrap realistic ungrammatical / grammatical pairs for training a corrector.
  arXiv  Detail & Related papers  (2021-09-14T17:06:43Z)
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction [49.25830718574892]
  We present a new framework named Tail-to-Tail (textbfTtT) non-autoregressive sequence prediction. Considering that most tokens are correct and can be conveyed directly from source to target, and the error positions can be estimated and corrected. Experimental results on standard datasets, especially on the variable-length datasets, demonstrate the effectiveness of TtT in terms of sentence-level Accuracy, Precision, Recall, and F1-Measure.
  arXiv  Detail & Related papers  (2021-06-03T05:56:57Z)
• Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction [98.31440090585376]
  Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. Existing GEC models tend to produce spurious corrections or fail to detect lots of errors. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses.
  arXiv  Detail & Related papers  (2021-05-10T15:04:25Z)
• A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction [54.569707226277735]
  Existing approaches for grammatical error correction (GEC) rely on supervised learning with manually created GEC datasets. There is a non-negligible amount of "noise" where errors were inappropriately edited or left uncorrected. We propose a self-refinement method where the key idea is to denoise these datasets by leveraging the prediction consistency of existing models.
  arXiv  Detail & Related papers  (2020-10-07T04:45:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.