A Holistic Framework for Automated Answer Scoring: Unifying Syntactic and Semantic Analysis
About this article
Keywords:
Automated Answer Scoring; RNN; LSTM; Natural Language Processing; RoBERTa; Syntactic Feature; Semantic Feature.Abstract
In educational and assessment contexts, automated response scoring is crucial, especially for effectively managing extensive assessments. This research integrates syntactic and semantic data to present a novel hybrid model to handle issues in this domain. Recognizing the value of integrating these complementary elements for improved comprehension and assessment accuracy, the model has modular components that extract syntactic and semantic information from responses. The hybrid model ensures a more reliable and flexible scoring system by combining rule-based approaches with machine learning and deep learning techniques in a unique way. The model gains more accuracy and adaptability by leveraging the advantages of each method, which enables it to be used in a variety of educational settings. Experiments were carried out utilizing a Hindi dataset to assess the hybrid model's efficacy. The model's performance was evaluated using key performance indicators, including as accuracy, precision, recall, and F1 score. The findings showed that the hybrid model works noticeably better than conventional scoring techniques, offering superior outcomes in terms of accuracy and flexibility. This suggests that the approach has the potential to completely transform automated answer scoring in educational settings that are bilingual and culturally diverse. All things considered, this hybrid strategy presents a viable way to enhance automated answer scoring systems. This model can improve the fairness and scalability of assessments across many languages and educational settings by combining syntactic and semantic elements and utilizing cutting-edge technologies, which will help create evaluation procedures that are more inclusive and dependable.
References
Sharma, R., et al. (2020). Leveraging Automated Scoring in Telecaller Recruitment: A Case Study of Startup Apna. International Conference on Information Systems, 128-140.
Kumar, S., & Kumar, A. (2021). Challenges in Hindi Natural Language Processing: A Review. International Journal of Computational Linguistics, 38(3), 412-426.
Singh, V., & Gupta, R. (2022). Advances in Hindi Natural Language Processing for Automated Scoring. ACM Transactions on Asian Language Information Processing, 21(1), 56-68.
Smith, A. (2018). Advancements in Rule-based Natural Language Processing Systems. Journal of Computational Linguistics, 35(2), 215-228.
Jones, B., et al. (2019). Machine Learning Models for Automated Answer Scoring: A Review. Educational Technology Research and Development, 67(4), 923-939.
View more references (18)
Johnson, C., & Brown, D. (2020). Rule-based Approaches to Automated Answer Scoring: Challenges and Opportunities. Journal of Educational Technology, 45(3), 421-435.
Garcia, M., et al. (2021). Enhancing Automated Answer Scoring with Machine Learning Techniques. International Journal of Artificial Intelligence in Education, 31(1), 87-102
Choi, H., et al. (2022). Integrating Syntactic and Semantic Features in Automated Scoring: A Hybrid Approach. International Conference on Arti-ficial Intelligence, 156-168.
Goldberg, Y. (2017). Neural Network Methods for Natural Language Processing. Synthesis Lectures on Human Language Technologies. https://doi.org/10.1007/978-3-031-02165-7.
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324.
Rajkomar, A., et al. (2018). Scalable and Accurate Deep Learning with Electronic Health Records. npj Digital Medicine, 1(1), 1-10.
Lipton, Z. C. (2016). The Mythos of Model Interpretability. arXiv preprint arXiv:1606.03490.
Kotsiantis, S. B., et al. (2007). Supervised Machine Learning: A Review of Classification Techniques. Emerging Artificial Intelligence Applications in Computer Engineering, 3(1), 3-24.
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Devlin, J., et al. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805.
Walia, T. S. Investigating the scope of semantic analysis in natural language processing considering accuracy and performance. In Recent Advances in Computing Sciences (pp. 323-328). CRC Press.
Walia, T. S. (2024). Hybrid Approach for Automated Answer Scoring Using Semantic Analysis in Long Hindi Text. Revue d'Intelligence Artificiel-le, 38(1). https://doi.org/10.18280/ria.380122.
Deepender, & Walia, T. S. (2022, November). Investigating the Role of Semantic Analysis in Automated Answer Scoring. In International Confer-ence on Innovations in Computational Intelligence and Computer Vision (pp. 559-571). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-99-2602-2_42.
Sanju, Kumar, V., & Kumari, P. (2024). Evaluating the Performance of Bayesian Approach for Imputing Missing Data under different Missingness Mechanism. Sankhya B, 1-11. https://doi.org/10.1007/s13571-024-00344-w.
Sanju, Kumar, V., & Deepender. (2023). Evaluation of imputation techniques for genotypic data of soybean crop under missing completely at ran-dom mechanism.
Singh, D. (2023). Non-linear growth models for acreage, production and productivity of food-grains in Haryana.
Shrivastava, U., & Verma, J. K. (2021, December). A Study on 5G Technology and Its Applications in Telecommunications. In 2021 International Conference on Computational Performance Evaluation (ComPE) (pp. 365-371). IEEE. https://doi.org/10.1109/ComPE53109.2021.9752402.
KUMAR, V., & Kumari, P. (2023). Analysis of Incomplete Data Under Different Missingness Mechanism using Imputation Methods for Wheat Genotypes. Current Agriculture Research Journal, 11(3). https://doi.org/10.12944/CARJ.11.3.33