Bloom’s Taxonomy based automatic Marathi question generation

In the current era of automation, various fields, including education, are undergoing transformations to enhance their existing processes. One crucial aspect in the field of education is examination management. Automatic question generation (AQG) for creating evaluation systems and question papers represents a significant transformation that schools, colleges, and universities are experiencing. Although significant research has been conducted in AQG for foreign languages, there is a scarcity of such work in Indian regional languages. Considering this, a novel working model for AQG for Marathi language texts was presented. The proposed research generates a diverse set of questions automatically through various natural language processing (NLP) pipeline activities, including tokenization, parts of speech (POS) tagging, stemming, named entity recognition (NER), shallow parsing, and dependency parsing. The generated questions fall into the categories of context-based and grammar-based questions, each elaborated in detail with scientific interpretation. This process contributes to the validation and refinement of our question generation methodology. A benchmarking approach using Bloom's Taxonomy was employed to validate the accuracy of the generated questions, ensuring they were aligned with educational objectives and targeted the desired levels of cognitive complexity. The empirical evaluation of the proposed methodology is conducted using the bilingual evaluation understudy (BLEU) score and manual scoring. The accuracy achieved using the BLEU score is 90.37% for the 'wh' questions, based on the corpus created from the sixth standard science textbook published by the Maharashtra State Board, Maharashtra, India. A diverse set of high-quality Marathi language questions has been successfully curated, suitable for compiling question papers aligned with Bloom's taxonomy levels.