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

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


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.
Anthology ID:
2021.findings-emnlp.231
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2713–2718
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.231
DOI:
10.18653/v1/2021.findings-emnlp.231
Bibkey:
Cite (ACL):
Xiao-Yu Guo, Yuan-Fang Li, and Gholamreza Haffari. 2021. Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2713–2718, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text (Guo et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.231.pdf
Software:
 2021.findings-emnlp.231.Software.zip
Video:
 https://aclanthology.org/2021.findings-emnlp.231.mp4
Data
DROP