AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

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 2021 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k test (overall)answer accuracy: 76.8 -> 79.5Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k test (Motion)answer accuracy: 76.9 -> 79.8Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k test (Task)answer accuracy: 79.0 -> 79.0No clear effect
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k test (Relation)answer accuracy: 76.0 -> 77.9Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k test (Price)answer accuracy: 83.6 -> 81.8Hurt
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k OOD (overall)answer accuracy: 45.8 -> 63.2Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k OOD (Motion)answer accuracy: 44.5 -> 65.0Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k OOD (Task)answer accuracy: 47.4 -> 64.8Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k OOD (Relation)answer accuracy: 55.1 -> 62.9Improved
Use SMART instead of the strongest reported baselinealgebra story problem solving · ASP6.6k OOD (Price)answer accuracy: 45.3 -> 60.8Improved
Add relation reasoning to NER-only parsing (ablation)SMART · ASP6.6k testanswer accuracy: around 20%Improved
Add Seq2Seq relation detection to the initial relation extraction module (ablation)SMART · ASP6.6k testanswer accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy