Chaining Simultaneous Thoughts for Numerical Reasoning

Zhihong Shao, Fei Huang, Minlie Huang


Abstract
Given that rich information is hidden behind ubiquitous numbers in text, numerical reasoning over text should be an essential skill of AI systems. To derive precise equations to solve numerical reasoning problems, previous work focused on modeling the structures of equations, and has proposed various structured decoders. Though structure modeling proves to be effective, these structured decoders construct a single equation in a pre-defined autoregressive order, potentially placing an unnecessary restriction on how a model should grasp the reasoning process. Intuitively, humans may have numerous pieces of thoughts popping up in no pre-defined order; thoughts are not limited to the problem at hand, and can even be concerned with other related problems. By comparing diverse thoughts and chaining relevant pieces, humans are less prone to errors. In this paper, we take this inspiration and propose CANTOR, a numerical reasoner that models reasoning steps using a directed acyclic graph where we produce diverse reasoning steps simultaneously without pre-defined decoding dependencies, and compare and chain relevant ones to reach a solution. Extensive experiments demonstrated the effectiveness of CANTOR under both fully-supervised and weakly-supervised settings.
Anthology ID:
2022.findings-emnlp.187
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2533–2547
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.187
DOI:
10.18653/v1/2022.findings-emnlp.187
Bibkey:
Cite (ACL):
Zhihong Shao, Fei Huang, and Minlie Huang. 2022. Chaining Simultaneous Thoughts for Numerical Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2533–2547, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Chaining Simultaneous Thoughts for Numerical Reasoning (Shao et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2022.findings-emnlp.187.pdf