# Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text

arXiv: https://arxiv.org/abs/2109.02289 · HTML: https://mlsanity.com/paper/2109.02289/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 12 of 12)

- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019)
- [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019)
- [A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning](https://mlsanity.com/paper/1908.05514/) (2019)
- [Question Directed Graph Attention Network for Numerical Reasoning over Text](https://mlsanity.com/paper/2009.07448/) (2020)
- [Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning](https://mlsanity.com/paper/2010.15877/) (2020)
- [Modeling Topical Relevance for Multi-Turn Dialogue Generation](https://mlsanity.com/paper/2009.12735/) (2020)
- [Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning](https://mlsanity.com/paper/2101.11802/) (2021)
- [Understanding Unnatural Questions Improves Reasoning over Text](https://mlsanity.com/paper/2010.09366/) (2020)

## Built on by (most cited first, 2 of 2)

- [NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering](https://mlsanity.com/paper/2211.03462/) (2022)
- [Teaching Neural Module Networks to Do Arithmetic](https://mlsanity.com/paper/2210.02703/) (2022)

## Abstract (arXiv)

Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Module Networks (NMNs), follows the programmer-interpreter paradigm and leverages specialised modules to perform compositional reasoning. However, the NMNs framework does not consider the relationship between numbers and entities in both questions and paragraphs. We propose effective techniques to improve NMNs' numerical reasoning capabilities by making the interpreter question-aware and capturing the relationship between entities and numbers. On the same subset of the DROP dataset for CQA on text, experimental results show that our additions outperform the original NMNs by 3.0 points for the overall F1 score.