EUVIMEDEUVIMED entdecken
Crossref

A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models

Hanqing Zhang, Haolin Song, Shaoyu Li, Ming Zhou, Dawei Song

ACM Computing Surveys · 31.03.2024 · 56 (3) · 1-37

DOI: 10.1145/3617680 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 06.10.2023. Verfasst von Hanqing Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 238-mal zitiert (Crossref) und nennt 172 Literaturangaben. Gefördert von: Natural Science Foundation of Beijing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Controllable Text Generation (CTG) is an emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used Transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the limited level of interpretability of deep neural networks, the controllability of these methods needs to be guaranteed. To this end, controllable text generation using Transformer-based PLMs has become a rapidly growing yet challenging new research hotspot. A diverse range of approaches have emerged in the past 3 to 4 years, targeting different CTG tasks that require different types of controlled constraints. In this article, we present a systematic critical review on the common tasks, main approaches, and evaluation methods in this area. Finally, we discuss the challenges that the field is facing, and put forward various promising future directions. To the best of our knowledge, this is the first survey article to summarize the state-of-the-art CTG techniques from the perspective of Transformer-based PLMs. We hope it can help researchers and practitioners in the related fields to quickly track the academic and technological frontier, providing them with a landscape of the area and a roadmap for future research.

Förderung

  • Natural Science Foundation of Beijing

Zitieren

APA

Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024). A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models. ACM Computing Surveys, 56(3), 1-37. https://doi.org/10.1145/3617680

Vancouver

Zhang H, Song H, Li S, Zhou M, Song D. A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models. ACM Computing Surveys. 2024;56(3):1-37. doi:10.1145/3617680

BibTeX
@article{Zhang2024,
  author = {Zhang, Hanqing and Song, Haolin and Li, Shaoyu and Zhou, Ming and Song, Dawei},
  title = {A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models},
  journal = {ACM Computing Surveys},
  year = {2024},
  volume = {56},
  number = {3},
  pages = {1--37},
  doi = {10.1145/3617680}
}
Kostenlos starten →