Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation
Multi-aspect controllable text generation aims to control the generated texts in attributes from multiple aspects (e.g., "positive" from sentiment and "sport" from topic). For ease of obtaining training samples, existing works neglect attribute correlations formed by the intertwining of different attributes. Particularly, the stereotype formed by imbalanced attribute correlations significantly affects multi-aspect control. In this paper, we propose MAGIC, a new multi-aspect controllable text generation method with disentangled counterfactual augmentation. We alleviate the issue of imbalanced attribute correlations during training using counterfactual feature vectors in the attribute latent space by disentanglement. During inference, we enhance attribute correlations by target-guided counterfactual augmentation to further improve multi-aspect control. Experiments show that MAGIC outperforms state-of-the-art baselines in both imbalanced and balanced attribute correlation scenarios. Our source code and data are available at https://github.com/nju-websoft/MAGIC.
Code (1)
Tasks
AttributecounterfactualDisentanglementText GenerationSimilar Papers 제목 키워드 기반
DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation
D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with r…
3D Shape GenerationTowards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models
Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are ofte…
AttributeText GenerationLearning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation
We consider the conditional generation of 3D drug-like molecules with \textit{explicit control} over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikeness or Synthetic Accessibili…
3D Molecule GenerationDrug DiscoveryContent-style disentangled representation for controllable artistic image stylization and generation
Controllable artistic image stylization and generation aims to render the content provided by text or image with the learned artistic style, where content and style decoupling is the key to achieve satisfactory results. …
DisentanglementImage StylizationComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity …
Image Generation