Skip to main content

Numerical question answering with Neural Module Networks

Primary supervisor

Yuan-Fang Li

Neural module networks (NMNs) [1] support explainable question answering over text [2] by parsing a natural-language question into a program. Such a program consists of a number of differentiable neural modules that can be executed on text in a soft way, operating over attention scores. As a result, NMNs learn to jointly program and execute these programs in an end-to-end way.

Designed mainly for compositional (multi-hop) reasoning, NMNs provide limited support for numerical reasoning. It only supports number comparison, finding min/max in a paragraph and date differences.

Student cohort

Single Semester
Double Semester


This project will design new modules that enhance the numerical reasoning capabilities of NMNs so that it can handle more complex questions.


  1. Andreas, J., Rohrbach, M., Darrell, T., & Klein, D. (2016). Neural module networks. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 39-48).

  2. Gupta, N., Lin, K., Roth, D., Singh, S., & Gardner, M. (2019). Neural module networks for reasoning over text. In International Conference on Learning Representations (ICLR).

Required knowledge

Natural language processing

Deep learning