mlsanityData to 7 Oct 2026

Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction

arXiv 2307.02127 ↗First posted 5 Jul 2023cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Grammatical Error Correction (GEC) is the task of correcting errorful sentences into grammatically correct, semantically consistent, and coherent sentences. Popular GEC models either use large-scale synthetic corpora or use a large number of human-designed rules. The former is costly to train, while the latter requires quite a lot of human expertise. In recent years, AMR, a semantic representation framework, has been widely used by many natural language tasks due to its completeness and flexibility. A non-negligible concern is that AMRs of grammatically incorrect sentences may not be exactly reliable. In this paper, we propose the AMR-GEC, a seq-to-seq model that incorporates denoised AMR as additional knowledge. Specifically, We design a semantic aggregated GEC model and explore denoising methods to get AMRs more reliable. Experiments on the BEA-2019 shared task and the CoNLL-2014 shared task have shown that AMR-GEC performs comparably to a set of strong baselines with a large number of synthetic data. Compared with the T5 model with synthetic data, AMR-GEC can reduce the training time by 32% while inference time is comparable. To the best of our knowledge, we are the first to incorporate AMR for grammatical error correction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

17 of 30 references.

References · 17

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2020GECToR -- Grammatical Error Correction: Tag, Not Rewritecited by 177
  4. 2021A Simple Recipe for Multilingual Grammatical Error Correctioncited by 108
  5. 2019Encode, Tag, Realize: High-Precision Text Editingcited by 99
  6. 2020Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correctioncited by 59
  7. 2019An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correctioncited by 55
  8. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  9. 2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Datacited by 50
  10. 2019Semantic Neural Machine Translation using AMRcited by 37
  11. 2020Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Modelcited by 33
  12. 2022SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parsercited by 32
5 more
  1. 2021Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answeringcited by 17
  2. 2020Copy that! Editing Sequences by Copying Spanscited by 13
  3. 2022Type-Driven Multi-Turn Corrections for Grammatical Error Correctioncited by 9
  4. 2022From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correctioncited by 7
  5. 2021A Syntax-Guided Grammatical Error Correction Model with Dependency Tree Correctioncited by 4

Built on by

Not cited yet.