Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models

2025-01-05

AI Summary

Bangla mathematical word problems (MWPs) suffer from a scarcity of high-quality datasets and effective models in low-resource language settings. Method: This paper introduces the first end-to-end solving framework for Bangla MWPs, comprising (i) the construction of PatiGonit—a large-scale, manually curated Bangla MWP dataset containing 10,000 problems—and (ii) a systematic evaluation of multilingual (mT5, mBART50) and monolingual (BanglaT5) Transformer models on equation generation, enhanced by syntax-aware sequence-to-sequence fine-tuning tailored to Bangla morphosyntax. Contribution/Results: mT5 achieves 97.30% equation accuracy—substantially outperforming all baselines—enabling the first high-precision, automatic conversion from natural-language Bangla problem descriptions to executable equations. The publicly released PatiGonit dataset and trained models constitute foundational infrastructure for low-resource educational AI, facilitating reproducible research and downstream applications in automated math reasoning.

Technology Category

• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Mathematical word problems (MWPs) involve the task of converting textual descriptions into mathematical equations. This poses a significant challenge in natural language processing, particularly for low-resource languages such as Bengali. This paper addresses this challenge by developing an innovative approach to solving Bengali MWPs using transformer-based models, including Basic Transformer, mT5, BanglaT5, and mBART50. To support this effort, the"PatiGonit"dataset was introduced, containing 10,000 Bengali math problems, and these models were fine-tuned to translate the word problems into equations accurately. The evaluation revealed that the mT5 model achieved the highest accuracy of 97.30%, demonstrating the effectiveness of transformer models in this domain. This research marks a significant step forward in Bengali natural language processing, offering valuable methodologies and resources for educational AI tools. By improving math education, it also supports the development of advanced problem-solving skills for Bengali-speaking students.

Problem

• Bengali Language
• Math Word Problems
• Low-Resource Environment

Innovation

• Transformer-based Models
• Bengali Mathematical Word Problems
• mT5 Accuracy