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

Source: [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](<https://www.sota2.com/research/paper/68fa6aab1e209131cea299ad>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:30:26.199Z

Authors: Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

Published: 2021-09-06T08:34:31.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.02289>)

[PDF](<https://arxiv.org/pdf/2109.02289.pdf>)