# Grammatical Error Correction for Code-Switched Sentences by Learners of English

arXiv: https://arxiv.org/abs/2404.12489 · HTML: https://mlsanity.com/paper/2404.12489/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 75 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Parallel Iterative Edit Models for Local Sequence Transduction](https://mlsanity.com/paper/1910.02893/) (2019)
- [A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies](https://mlsanity.com/paper/2301.01967/) (2023)
- [Seq2Edits: Sequence Transduction Using Span-level Edit Operations](https://mlsanity.com/paper/2009.11136/) (2020)
- [Are Multilingual Models Effective in Code-Switching?](https://mlsanity.com/paper/2103.13309/) (2021)
- [Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models](https://mlsanity.com/paper/2105.13318/) (2021)
- [An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction](https://mlsanity.com/paper/1909.00502/) (2019)
- [Corpora Generation for Grammatical Error Correction](https://mlsanity.com/paper/1904.05780/) (2019)
- [HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text](https://mlsanity.com/paper/2107.03760/) (2021)
- [Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation](https://mlsanity.com/paper/1811.02356/) (2018)
- [Can You Traducir This? Machine Translation for Code-Switched Input](https://mlsanity.com/paper/2105.04846/) (2021)
- [Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation](https://mlsanity.com/paper/2310.20470/) (2023)
- [Artificial Error Generation with Machine Translation and Syntactic Patterns](https://mlsanity.com/paper/1707.05236/) (2017)
- [CALCS 2021 Shared Task: Machine Translation for Code-Switched Data](https://mlsanity.com/paper/2202.09625/) (2022)

## Built on by (most cited first, 2 of 2)

- [Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text](https://mlsanity.com/paper/2506.14012/) (2025)
- [LLM-based Code-Switched Text Generation for Grammatical Error Correction](https://mlsanity.com/paper/2410.10349/) (2024)

## Abstract (arXiv)

Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar Error Correction (GEC) systems have been trained on monolingual data and not developed with CSW in mind. In this work, we conduct the first exploration into the use of GEC systems on CSW text. Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora. We then investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints, and identify how they affect the performance of GEC systems on CSW text. Our best model achieves an average increase of 1.57 F0.5 across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model's performance on a monolingual dataset. We furthermore discovered that models trained on one CSW language generalise relatively well to other typologically similar CSW languages.