Teaching Neural Module Networks to Do Arithmetic

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


Abstract
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks (NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However, NMNs only have limited reasoning abilities, and lack numerical reasoning capability. We upgrade NMNs by: (a) bridging the gap between its interpreter and the complex questions; (b) introducing addition and subtraction modules that perform numerical reasoning over numbers. On a subset of DROP, experimental results show that our proposed methods enhance NMNs’ numerical reasoning skills by 17.7% improvement of F1 score and significantly outperform previous state-of-the-art models.
Anthology ID:
2022.coling-1.129
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1502–1510
Language:
URL:
https://aclanthology.org/2022.coling-1.129
DOI:
Bibkey:
Cite (ACL):
Jiayi Chen, Xiao-Yu Guo, Yuan-Fang Li, and Gholamreza Haffari. 2022. Teaching Neural Module Networks to Do Arithmetic. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1502–1510, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Teaching Neural Module Networks to Do Arithmetic (Chen et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.129.pdf
Data
DROP