Daniel Ciao — accepted AI-conference papers

2021

Learning by Fixing: Solving Math Word Problems with Weak Supervision

Yining Hong, Qing Li, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

AAAI 2021technical

Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. In this paper, we address this issue by introducing a weakly-supervised paradigm for learning MWPs. Our method only requires the annotations of the final answers and can gen…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2021

SMART: A Situation Model for Algebra Story Problems via Attributed Grammar

Yining Hong, Qing Li, Ran Gong, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

AAAI 2021technical

Solving algebra story problems remains a challenging task in artificial intelligence, which requires a detailed understanding of real-world situations and a strong mathematical reasoning capability. Previous neural solvers of math word problems directly translate problem texts into equations, lackin…

Cited by 37 Source ↗PDF ↗Scholar ↗