EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions

Mingye Wang, Pan Xie, Yao Du, Xiaohui Hu

Applied Sciences · 14.06.2023 · 13 (12) · 7111

DOI: 10.3390/app13127111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 14.06.2023. Verfasst von Mingye Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: key R&D project of the Ministry of Science and Technology of the People’s Republic of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text summarization is a prominent task in natural language processing (NLP) that condenses lengthy texts into concise summaries. Despite the success of existing supervised models, they often rely on datasets of well-constructed text pairs, which can be insufficient for languages with limited annotated data, such as Chinese. To address this issue, we propose a semi-supervised learning method for text summarization. Our method is inspired by the cycle-consistent adversarial network (CycleGAN) and considers text summarization as a style transfer task. The model is trained by using a similar procedure and loss function to those of CycleGAN and learns to transfer the style of a document to its summary and vice versa. Our method can be applied to multiple languages, but this paper focuses on its performance on Chinese documents. We trained a T5-based model and evaluated it on two datasets, CSL and LCSTS, and the results demonstrate the effectiveness of the proposed method.

Förderung

  • key R&D project of the Ministry of Science and Technology of the People’s Republic of China

Zitieren

APA

Wang, M., Xie, P., Du, Y., & Hu, X. (2023). T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions. Applied Sciences, 13(12), 7111. https://doi.org/10.3390/app13127111

Vancouver

Wang M, Xie P, Du Y, Hu X. T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions. Applied Sciences. 2023;13(12):7111. doi:10.3390/app13127111

BibTeX
@article{Wang2023,
  author = {Wang, Mingye and Xie, Pan and Du, Yao and Hu, Xiaohui},
  title = {T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {12},
  pages = {7111},
  doi = {10.3390/app13127111}
}
Kostenlos starten →