mlsanityData to 7 Oct 2026

Comparison of Grammatical Error Correction Using Back-Translation Models

arXiv 2104.07848 ↗First posted 16 Apr 2021cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Grammatical error correction (GEC) suffers from a lack of sufficient parallel data. Therefore, GEC studies have developed various methods to generate pseudo data, which comprise pairs of grammatical and artificially produced ungrammatical sentences. Currently, a mainstream approach to generate pseudo data is back-translation (BT). Most previous GEC studies using BT have employed the same architecture for both GEC and BT models. However, GEC models have different correction tendencies depending on their architectures. Thus, in this study, we compare the correction tendencies of the GEC models trained on pseudo data generated by different BT models, namely, Transformer, CNN, and LSTM. The results confirm that the correction tendencies for each error type are different for every BT model. Additionally, we examine the correction tendencies when using a combination of pseudo data generated by different BT models. As a result, we find that the combination of different BT models improves or interpolates the F_0.5 scores of each error type compared with that of single BT models with different seeds.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 39 of its 67 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

39 of 67 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  8. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  9. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  10. 2017Convolutional Sequence to Sequence Learningcited by 550
  11. 2017Six Challenges for Neural Machine Translationcited by 334
  12. 2018Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networkscited by 101
27 more
  1. 2017JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correctioncited by 96
  2. 2019Tagged Back-Translationcited by 76
  3. 2020Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correctioncited by 59
  4. 2017Neural Language Modeling by Jointly Learning Syntax and Lexiconcited by 57
  5. 2018Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Taskcited by 56
  6. 2019An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correctioncited by 55
  7. 2019Corpora Generation for Grammatical Error Correctioncited by 53
  8. 2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Datacited by 50
  9. 2019On The Evaluation of Machine Translation Systems Trained With Back-Translationcited by 40
  10. 2018A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correctioncited by 36
  11. 2019A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learningcited by 26
  12. 2020Dynamic Data Selection and Weighting for Iterative Back-Translationcited by 25
  13. 2016GLEU Without Tuningcited by 24
  14. 2018Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Studycited by 22
  15. 2019Generalizing Back-Translation in Neural Machine Translationcited by 18
  16. 2019Improving Grammatical Error Correction with Machine Translation Pairscited by 17
  17. 2018Investigating Backtranslation in Neural Machine Translationcited by 14
  18. 2017A Nested Attention Neural Hybrid Model for Grammatical Error Correctioncited by 12
  19. 2019Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewritingcited by 12
  20. 2017Artificial Error Generation with Machine Translation and Syntactic Patternscited by 11
  21. 2018Wronging a Right: Generating Better Errors to Improve Grammatical Error Detectioncited by 11
  22. 2019Learning to combine Grammatical Error Correctionscited by 9
  23. 2019The Unbearable Weight of Generating Artificial Errors for Grammatical Error Correctioncited by 8
  24. 2019Controllable Data Synthesis Method for Grammatical Error Correctioncited by 8
  25. 2020Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translationcited by 7
  26. 2018Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translationcited by 6
  27. 2020Pseudo-Bidirectional Decoding for Local Sequence Transductioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1; 2025: 2.

9 papers.

  1. 2022Grammatical Error Correction: A Survey of the State of the Artcited by 43
  2. 2023Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methodscited by 37
  3. 2022Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyondcited by 20
  4. 2025Out of Style: RAG's Fragility to Linguistic Variationcited by 10
  5. 2024A Comparative Analysis of Noise Reduction Methods in Sentiment Analysis on Noisy Bangla Textscited by 3
  6. 2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correctioncited by 2
  7. 2023Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmentingcited by 2
  8. 2025Data Augmentation for Spoken Grammatical Error Correctioncited by 1
  9. 2022Evaluation of large-scale synthetic data for Grammar Error Correctioncited by 0