Chaining Simultaneous Thoughts for Numerical Reasoning
Shao, Zhihong, Huang, Fei, Huang, Minlie
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Nov-29-2022
- Country:
- North America
- Dominican Republic (0.04)
- United States
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- San Diego County > San Diego (0.04)
- Los Angeles County > Long Beach (0.04)
- Minnesota > Hennepin County
- Canada > British Columbia
- Europe
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Spain > Catalonia
- Asia
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- North America
- Genre:
- Research Report > New Finding (0.34)
- Technology: