Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910997496725504 |
|---|---|
| author | Qwaider, Chatrine Alhafni, Bashar Chirkunov, Kirill Habash, Nizar Briscoe, Ted |
| author_facet | Qwaider, Chatrine Alhafni, Bashar Chirkunov, Kirill Habash, Nizar Briscoe, Ted |
| contents | Automated Essay Scoring (AES) plays a crucial role in assessing language learners' writing quality, reducing grading workload, and providing real-time feedback. The lack of annotated essay datasets inhibits the development of Arabic AES systems. This paper leverages Large Language Models (LLMs) and Transformer models to generate synthetic Arabic essays for AES. We prompt an LLM to generate essays across the Common European Framework of Reference (CEFR) proficiency levels and introduce and compare two approaches to error injection. We create a dataset of 3,040 annotated essays with errors injected using our two methods. Additionally, we develop a BERT-based Arabic AES system calibrated to CEFR levels. Our experimental results demonstrate the effectiveness of our synthetic dataset in improving Arabic AES performance. We make our code and data publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17739 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection Qwaider, Chatrine Alhafni, Bashar Chirkunov, Kirill Habash, Nizar Briscoe, Ted Computation and Language Automated Essay Scoring (AES) plays a crucial role in assessing language learners' writing quality, reducing grading workload, and providing real-time feedback. The lack of annotated essay datasets inhibits the development of Arabic AES systems. This paper leverages Large Language Models (LLMs) and Transformer models to generate synthetic Arabic essays for AES. We prompt an LLM to generate essays across the Common European Framework of Reference (CEFR) proficiency levels and introduce and compare two approaches to error injection. We create a dataset of 3,040 annotated essays with errors injected using our two methods. Additionally, we develop a BERT-based Arabic AES system calibrated to CEFR levels. Our experimental results demonstrate the effectiveness of our synthetic dataset in improving Arabic AES performance. We make our code and data publicly available. |
| title | Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.17739 |