Research map / Image generation / Text-to-image diffusion
Complementary Auxiliary Classifiers for Label-Conditional Text Generation
Yuan Li, Chunyuan Li, Yizhe Zhang, Xiujun Li, Guoqing Zheng, Lawrence Carin, Jianfeng Gao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add complementary output-space classifier (CARA vs ARAE-) (ablation) | ARAE- · Yelp conditional generation | G-score: 40.74 -> 52.48 | Improved |
| add complementary output-space classifier (CARA vs ARAE-) (ablation) | ARAE- · Yahoo conditional generation | G-score: 33.33 -> 40.31 | Improved |
| add annealing schedule for classifier weight (ablation) | CARA · Yelp conditional generation | G-score: 52.48 -> 54.50 | Improved |
| add annealing schedule for classifier weight (ablation) | CARA · Yahoo conditional generation | G-score: 40.31 -> 41.81 | Improved |
| add annealing schedule for classifier weight (ablation) | CARA · Style captioning conditional generation | G-score: 46.92 -> 50.52 | Improved |
| add annealing schedule for classifier weight (ablation) | CARA · Yelp attribute transfer | G-score: 63.26 -> 65.40 | Improved |
| add annealing schedule for classifier weight (ablation) | CARA · Personality captioning attribute transfer | G-score: 44.48 -> 40.65 | Hurt |
| replace encoder with BERT (ablation) | CARA + annealing · Yelp conditional generation | G-score: 54.50 -> 59.44 | Improved |
| replace encoder with BERT (ablation) | CARA + annealing · Yahoo conditional generation | G-score: 41.81 -> 46.19 | Improved |
| replace encoder with BERT (ablation) | CARA + annealing · Personality captioning conditional generation | G-score: 34.46 -> 33.95 | Hurt |
| replace encoder with BERT (ablation) | CARA + annealing · Yelp attribute transfer | G-score: 65.40 -> 71.29 | Improved |
| replace encoder with BERT (ablation) | CARA + annealing · Style captioning attribute transfer | G-score: 7.36 -> 30.14 | Improved |
Closest papers by meaning
- Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach (AAAI 2024 · similarity 0.86)
- From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning (ECCV 2026 · similarity 0.85)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.84)
- Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification (AAAI 2024 · similarity 0.84)
- Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions (ICLR 2024 · similarity 0.84)
- SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation (ICLR 2025 · similarity 0.83)
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.
