A Hierarchical Latent Modulation Approach for Controlled Text Generation

Jincheng Zou, Guorong Chen (), Jian Wang, Bao Zhang, Hong Hu and Cong Liu
Additional contact information
Jincheng Zou: Department of School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, Chongqing 401331, China
Guorong Chen: Department of School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, Chongqing 401331, China
Jian Wang: Department of School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, Chongqing 401331, China
Bao Zhang: Department of School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, Chongqing 401331, China
Hong Hu: Department of School of Computer Science and Engineering (School of Artificial Intelligence), Chongqing University of Science and Technology, Chongqing 401331, China
Cong Liu: School of Economics and Management, Harbin Normal University, Harbin 150500, China

Mathematics, 2025, vol. 13, issue 5, 1-18

Abstract: Generative models based on Variational Autoencoders (VAEs) represent an important area of research in Controllable Text Generation (CTG). However, existing approaches often do not fully exploit the potential of latent variables, leading to limitations in both the diversity and thematic consistency of the generated text. To overcome these challenges, this paper introduces a new framework based on Hierarchical Latent Modulation (HLM). The framework incorporates a hierarchical latent space modulation module for the generation and embedding of conditional modulation parameters. By using low-rank tensor factorization (LMF), the approach combines multi-layer latent variables and generates modulation parameters based on conditional labels, enabling precise control over the features during text generation. Additionally, layer-by-layer normalization and random dropout mechanisms are employed to address issues such as the under-utilization of conditional information and the collapse of generative patterns. We performed experiments on five baseline models based on VAEs for conditional generation, and the results demonstrate the effectiveness of the proposed framework.

Keywords: controllable text generation; latent variables; hierarchical latent modulation; conditional modulation parameters (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/5/713/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/5/713/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:5:p:713-:d:1597480

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().