A Distributional Lens for Multi-Aspect Controllable Text Generation

15Citations
Citations of this article
32Readers
Mendeley users who have this article in their library.

Abstract

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 these controllers. To address this, we provide observations on attribute fusion from a distributional perspective and propose to directly search for the intersection areas of multiple attribute distributions as their combination for generation. Our method first estimates the attribute space with an autoencoder structure. Afterward, we iteratively approach the intersections by jointly minimizing distances to points representing different attributes. Finally, we map them to attribute-relevant sentences with a prefix-tuning-based decoder. Experiments on the three-aspect control task, including sentiment, topic, and detoxification aspects, reveal that our method outperforms several strong baselines on attribute relevance and text quality and achieves the SOTA. Further analysis also supplies some explanatory support for the effectiveness of our approach.

Cite

CITATION STYLE

APA

Gu, Y., Feng, X., Ma, S., Zhang, L., Gong, H., & Qin, B. (2022). A Distributional Lens for Multi-Aspect Controllable Text Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 (pp. 1023–1043). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.emnlp-main.67

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free