Abstract
In the recent past, solving mathematical word problems of varying complexities has gained popularity among researchers, for which Natural Language Processing (NLP) and Understanding (NLU) techniques, Machine Learning, Deep learning and several artificial intelligence (AI) based approaches are widely used. The paper presents a work aiming to solve single-sentence mathematical or arithmetic word problems or queries given in natural language (English). The work involves identification of problem types, simplification of the given word problem to extract the operators and the operands, mapping the operators to appropriate operands to create the mathematical expression and solve the query to generate the final result. We developed a dataset consisting of 430 diverse arithmetic word problems of different complexity levels. Our natural language calculator was evaluated on this dataset and it resulted in 86.28% accuracy.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
