Lingyuan Zhang — accepted AI-conference papers

2023

Controllable Text Generation via Probability Density Estimation in the Latent Space

Yuxuan Gu, Xiaocheng Feng, Sicheng Ma, Lingyuan Zhang, Heng Gong, Weihong Zhong +1

ACL 2023long

Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-specific classifiers or sampling one from relevant discrete samples. However, they cannot effectively model a complex space with diverse attributes…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗

2022

A Distributional Lens for Multi-Aspect Controllable Text Generation

Yuxuan Gu, Xiaocheng Feng, Sicheng Ma, Lingyuan Zhang, Heng Gong, Bing Qin

EMNLP 2022main

Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multiple controllers learned from single-aspect, but suffer from attribute degeneration caused by the mutual interference of…

Cited by 34 Source ↗PDF ↗code ↗Scholar ↗