H-AES: Towards Automated Essay Scoring for Hindi

Authors

  • Shubhankar Singh Manipal University Jaipur
  • Anirudh Pupneja BITS Pilani, K K Birla Goa Campus
  • Shivaansh Mital Indraprastha Institute of Information Technology, Delhi
  • Cheril Shah Pune Institute of Computer Technology
  • Manish Bawkar Sardar Vallabhbhai National Institute of Technology, Surat
  • Lakshman Prasad Gupta University of Allahabad
  • Ajit Kumar Indraprastha Institute of Information Technology, Delhi
  • Yaman Kumar Indraprastha Institute of Information Technology, Delhi
  • Rushali Gupta Banaras Hindu University
  • Rajiv Ratn Shah Indraprastha Institute of Information Technology, Delhi

DOI:

https://doi.org/10.1609/aaai.v37i13.26894

Keywords:

Automated Essay Scoring, Natural Language Processing, Hindi NLP, AI For Education, Low-Resource Languages, Machine Learning, Large-Language Models, LSTM Networks

Abstract

The use of Natural Language Processing (NLP) for Automated Essay Scoring (AES) has been well explored in the English language, with benchmark models exhibiting performance comparable to human scorers. However, AES in Hindi and other low-resource languages remains unexplored. In this study, we reproduce and compare state-of-the-art methods for AES in the Hindi domain. We employ classical feature-based Machine Learning (ML) and advanced end-to-end models, including LSTM Networks and Fine-Tuned Transformer Architecture, in our approach and derive results comparable to those in the English language domain. Hindi being a low-resource language, lacks a dedicated essay-scoring corpus. We train and evaluate our models using translated English essays and empirically measure their performance on our own small-scale, real-world Hindi corpus. We follow this up with an in-depth analysis discussing prompt-specific behavior of different language models implemented.

Downloads

Published

2023-09-06

How to Cite

Singh, S., Pupneja, A., Mital, S., Shah, C., Bawkar, M., Gupta, L. P., Kumar, A., Kumar, Y., Gupta, R., & Ratn Shah, R. (2023). H-AES: Towards Automated Essay Scoring for Hindi. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15955-15963. https://doi.org/10.1609/aaai.v37i13.26894