Mathematical Word Problem Solving Using Natural Language Processing

  • Shounaak UghadeEmail author
  • Satish Kumbhar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1077)


Natural language processing (NLP) is generally done on large data. Due to limited data word problem solving is challenging using NLP. There are some approaches proposed which could solve basic arithmetic problems like addition/subtraction. Knowledge representation is the main task to be done by NLP. Each kind of problem has its own approach. In this paper three types of mathematical word problems have been solved. Two of them are aptitude problems while the other two are reasoning problems. The spacy library has been used for effective use of Named Entity Recognition (NER) and word vectors. Stepwise solution has been generated instead of just answers which helps in improving understanding. The quite generic rather intuitive approach can be extended to solve some other kind of aptitude problems.


Knowledge representation Natural language processing Sentiment analysis Named entity recognition 


  1. 1.
    Sundaram, S.S., Khemani, D.: Natural language processing for solving simple word problems (2015)Google Scholar
  2. 2.
    Huang, D., Liu, J., Lin, C.-Y., Yin, J.: Neural math word problem solver with reinforcement learning (2018)Google Scholar
  3. 3.
    Shi, S., Wang, Y., Lin, C.-Y., Liu, X., Rui, Y.: Automatically solving number word problems by semantic parsing and reasoning (2015)Google Scholar
  4. 4.
    Amnueypornsakul, B., Bhat, S.: Machine-guided solution to mathematical word problems (MWP) (2014)Google Scholar
  5. 5.
    A novel framework for math word problem solving. Int. J. Inf. Educ. Technol. 3(1) (2013)Google Scholar
  6. 6.
    Kushman, N., Artzi, Y., Zettlemoyer, L., Barzilay, R.: Learning to automatically solve algebra word problems. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology and Computer Science & Engineering, University of WashingtonGoogle Scholar
  7. 7.
    Miyani, M., Doshi, S., Jain, J.: Word problem solver system using artificial intelligence. Proc. Comput. Sci. (ICACTA) 45, 800–807 (2015)CrossRefGoogle Scholar
  8. 8.
    Ma, Y., Tan, K., Shao, L., Shang, X.: Constructing the representation model of arithmetic word problems for intelligent tutoring system (2011)Google Scholar
  9. 9.
    Hevapathige, A., Wellappili, D., Kankanamge, G.U., Dewappriya, N., Ranathunga, S.: Two-phase classifier for automatic answer generation for math word problems (2018)Google Scholar
  10. 10.
    Dewappriya, N., Kankanamge, G.U., Wellappili, D., Hevapathige, A., Ranathunga, S.: Unit conflict resolution for automatic math word problem solving (2018)Google Scholar
  11. 11.
  12. 12.
  13. 13.
  14. 14.

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Computer Engineering and ITCollege of EngineeringPuneIndia

Personalised recommendations