AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

FR: Folded Rationalization with a Unified Encoder

Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, YuanKai Zhang

NeurIPS 2022 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 5 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
Share the generator and predictor encoderRationalization on Beer Reviews and Hotel Reviews · Six aspects in the main comparisonF1: 72.5 -> 82.8; 63.2 -> 73.4; 65.5 -> 67.0; 53.1 -> 57.1; 43.3 -> 44.8; 33.7 -> 38.7Improved
Share the generator and predictor encoderRationalization at low sparsity · Beer Reviews — AppearanceF1: 64.7 -> 63.2Hurt
Share the generator and predictor encoderRationalization at low sparsity · Beer Reviews — Aroma and PalateF1: 57.3 -> 68.2; 51.7 -> 61.8Improved
Share the generator and predictor encoderRationalization with a skewed predictor · Beer Reviews — Aroma and Palate, skew10–skew20F1: 61.5 -> 72.8; 49.3 -> 69.6; 11.0 -> 70.6; 5.5 -> 57.7; 1.3 -> 54.5; 0.6 -> 52.9Improved
Share the generator and predictor encoderRationalization with a deliberately skewed generator · Beer Reviews — Palate, skew60.0–skew75.0F1: 43.9 -> 59.6; 42.7 -> 63.4; 10.8 -> 58.1; 8.8 -> 51.0Improved
Share only the first GRU layer rather than all three (ablation)Three-layer encoder rationalization · Beer-AromaF1: 74.9 -> 65.4Hurt
Share the first two GRU layers rather than all three (ablation)Three-layer encoder rationalization · Beer-AromaF1: 74.9 -> 74.2Hurt
Share only the third GRU layer rather than all three (ablation)Three-layer encoder rationalization · Beer-AromaF1: 74.9 -> 64.1Hurt
Share the second and third GRU layers rather than all three (ablation)Three-layer encoder rationalization · Beer-AromaF1: 74.9 -> 71.7Hurt
Share only the first GRU layer rather than all three (ablation)Three-layer encoder rationalization · Hotel-CleanlinessF1: 38.3 -> 7.6Hurt
Share the first two GRU layers rather than all three (ablation)Three-layer encoder rationalization · Hotel-CleanlinessF1: 38.3 -> 21.8Hurt
Share only the third GRU layer rather than all three (ablation)Three-layer encoder rationalization · Hotel-CleanlinessF1: 38.3 -> 34.0Hurt

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