Training a Bespoke Grammatical Error Correction Model for Azerbaijani EFL Learners: A Low-Resource NLP Innovation for Educational Enhancement
DOI:
https://doi.org/10.69760/egjlle.2504002Keywords:
Grammatical Error Correction, Azerbaijani EFL Learners, Low-Resource NLP, Automated FeedbackAbstract
This paper presents a custom-trained grammatical error correction (GEC) system tailored to the specific L1 interference patterns of Azerbaijani English-as-Foreign-Language (EFL) learners. By collecting and annotating 3,000 learner sentences (incorrect-correct pairs) and fine-tuning a modern large language model (LLM), we demonstrate that a localized GEC model outperforms off-the-shelf tools like Grammarly and GPT-3.5. The custom model achieved a precision of 0.78 and F₀.₅ score of 0.74, compared to 0.59 for Grammarly and 0.68 for GPT-3.5 (Table 1). Notably, it corrected errors in articles, prepositions, verb tenses, and subject–verb agreement more accurately (Table 2). These results underscore the impact of L1-specific data on model effectiveness. We discuss implications for EFL pedagogy, local NLP development, and equitable AI, noting that incorporating learners’ native language patterns (L1 transfer) can significantly improve automated feedback. Ethical considerations such as data privacy and algorithmic fairness are addressed. This work illustrates how focused NLP innovation in low-resource settings can create practical AI tools that support language learning more effectively than generic systems.
References
Alismail, H. A. (2020). The role of AI-based writing tools in EFL learning. International Journal of Education and Research.
Asadova, B. (2025). Effective Strategies for Teaching Phonetics in the Classroom. Global Spectrum of Research and Humanities , 1(1), 12-18. https://doi.org/10.69760/gsrh.0101202402
Bryant, C., Felice, M., Andersen, Ø. E., & Briscoe, T. (2019). The BEA-2019 Shared Task on Grammatical Error Correction. Proceedings of the 2019 Workshop on Innovative Use of NLP for Building Educational Applications, 52–75. https://doi.org/10.18653/v1/W19-4406
Cummins, J., & Davison, C. (2007). International Handbook of English Language Teaching. Springer.
Dahlmeier, D., & Ng, H. T. (2012). Better evaluation for grammatical error correction. NAACL HLT 2012: Human Language Technologies, 568–572.
Edutopia. (2024). AI and the Law: What Educators Need to Know. Retrieved from https://www.edutopia.org/article/laws-ai-education
Gilquin, G., & Granger, S. (2015). From design to collection of learner corpora. In S. Granger, G. Gilquin, & F. Meunier (Eds.), The Cambridge Handbook of Learner Corpus Research (pp. 9–34). Cambridge University Press.
Granger, S., Dagneaux, E., & Meunier, F. (2009). International Corpus of Learner English (Version 2) [Computer corpus]. Presses Universitaires de Louvain.
Grundkiewicz, R., Junczys-Dowmunt, M., & Heafield, K. (2019). Near human-level performance in GEC with hybrid training. Proceedings of the 2019 Workshop on Innovative Use of NLP for Building Educational Applications, 8–15. https://doi.org/10.18653/v1/W19-4401
Hajiyeva, K. (2024). Common English Language Errors in Academic Writing Made by Azerbaijani Students.
Khudaverdiyeva, T. (2025). The Importance of Writing in Language Acquisition: A Cognitive, Communicative, and Pedagogical Perspective. Global Spectrum of Research and Humanities , 2(3), 127-138. https://doi.org/10.69760/gsrh.0203025014
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30.
Meegle. (2025). AI Ethics and Language Learning. Retrieved from https://www.meegle.com/en_us/topics/ai-ethics/ai-ethics-and-language-learning
Mirzayev, E. (2024). A Comprehensive Guide to English’s Most Common Vowel Sound. Global Spectrum of Research and Humanities , 1(1), 19-26. https://doi.org/10.69760/gsrh.0101202403
Napoles, C., Sakaguchi, K., & Tetreault, J. (2017). JFLEG: A Fluency Corpus and Benchmark for GEC. Proceedings of EACL 2017: Short Papers, 229–234. https://doi.org/10.1162/tacl_a_00068
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD, 1135–1144. https://doi.org/10.1145/2939672.2939778
Sadigova, S. (2024). A Comparative Analysis of Idiomatic Expressions in English and Azerbaijani: Cultural and Linguistic Insights. Acta Globalis Humanitatis Et Linguarum, 1(1), 158-167. https://doi.org/10.69760/aghel.024061
Sadigzade, Z. (2025). AI-Powered Feedback in ESL Writing Classes: Pedagogical Opportunities and Ethical Concerns. Journal of Azerbaijan Language and Education Studies, 2(4), 5-17. https://doi.org/10.69760/jales.2025004000
Sadiqzade, Z. (2024). Fostering Emotional Intelligence in Language Learners. Journal of Azerbaijan Language and Education Studies, 1(1), 67-76. https://doi.org/10.69760/jales.2024.00106
Sadiqzade, Z. (2024). The Impact of Music on Language Learning: A Harmonious Path to Mastery. EuroGlobal Journal of Linguistics and Language Education, 1(1), 134-140. https://doi.org/10.69760/zma1bn56
Sadiqzade, Z. (2025). Strengthening Language Skills Through Active Classroom Interaction. Global Spectrum of Research and Humanities , 2(1), 28-33. https://doi.org/10.69760/gsrh.01012025003
Safarova, L. (2024). Comparative Analysis of Azerbaijani and English Phonetic Systems. EuroGlobal Journal of Linguistics and Language Education, 1(2), 17–25. https://doi.org/10.69760/73vjgs24
Zeynalova, K. (2024). Comparative Typology of Azerbaijani and English: A Focus on the Non-Finite Forms of Verbs. Acta Globalis Humanitatis Et Linguarum, 1(2), 112-123. https://doi.org/10.69760/aghel.01024071
Downloads
Published
Issue
Section
License
Copyright (c) 2025 EuroGlobal Journal of Linguistics and Language Education
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
