AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Compositional Generalization by Learning Analytical Expressions

Qian Liu, Shengnan An, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, Dongmei Zhang

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 29 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
add Composer module (vs tree-to-sequence degeneration) (ablation)LAnE · SCAN Add Jumpaccuracy: 0.0 -> 100.0Improved
add Composer module (ablation)LAnE · SCAN Lengthaccuracy: 11.1 -> 100.0Improved
add Composer module (ablation)LAnE · SCAN MCD1accuracy: 5.3 -> 100.0Improved
add curriculum learning by input length (ablation)LAnE · all SCAN tasksaccuracy: 0.0 -> 100.0Improved
add simplicity-based reward to similarity reward (ablation)LAnE · SCAN Around Rightaccuracy: 0.0 -> 100.0Improved
add simplicity-based reward to similarity reward (ablation)LAnE · SCAN MCD3accuracy: 78.8 -> 100.0Improved
add simplicity-based reward to similarity reward (ablation)LAnE · SCAN Add Jump, Length, MCD1, MCD2accuracy: 100.0 -> 100.0No clear effect
use differential learning rates for Composer and Solver (vs other combinations) (ablation)LAnE · SCANtrain/test 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