EUVIMEDEUVIMED entdecken
Crossref

PromptCNER: A Segmentation-based Method for Few-shot Chinese NER with Prompt-tuning

Cheng-Cheng Mai, Yu Chen, Ziyu Gong, Hanxiang Wang, Mengchuan Qiu, Chunfeng Yuan, Yihua Huang

ACM Transactions on Asian and Low-Resource Language Information Processing · 30.09.2025 · 24 (9) · 1-24

DOI: 10.1145/3705314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 11.09.2025. Verfasst von Cheng-Cheng Mai und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Jiangsu Province Science & Tech Research Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recognizing Chinese entities in low-resource settings is a challenging but promising task, which extracts structured pre-defined entities and corresponding types from unstructured text. Compared with the prosperous Named Entity Recognition (NER) methods for Indo-European languages, such as English, the research on Chinese NER is still in its infancy. The main obstacles to the development of Chinese NER methods include the ambiguity of Chinese entity boundary recognition and limited data resources. To address these issues, in this paper, a word-segmentation-based model is present for few-shot Chinese NER. First, we enumerate all possible candidate entity spans on the character level for accurate entity boundary identification with the proposed word segmentation and combination strategy. Then, one kind of question-answer-based prompt template loaded with the candidate entity spans is proposed to cast entity extraction into the masked token prediction task, for dealing with the low-data problem by taking full advantage of the generality and transferability of the pre-trained language model. The extensive experimental results show that our method outperforms the state-of-the-art baselines in low-data settings and also achieves comparable performance in full-data settings.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Jiangsu Province Science & Tech Research Program
  • Jiangsu Province Science & Technology Research
  • Key R&D Program Project of Nanjng Jiangbei New Area
  • Open project of State Key Laboratory for Novel Software Technology, Nanjing University
  • Jiangsu Province Frontier Technology Research and Development Program
  • Collaborative Innovation Center of Novel Software Technology and Industrialization

Zitieren

APA

Mai, C., Chen, Y., Gong, Z., Wang, H., Qiu, M., Yuan, C., & Huang, Y. (2025). PromptCNER: A Segmentation-based Method for Few-shot Chinese NER with Prompt-tuning. ACM Transactions on Asian and Low-Resource Language Information Processing, 24(9), 1-24. https://doi.org/10.1145/3705314

Vancouver

Mai C, Chen Y, Gong Z, Wang H, Qiu M, Yuan C, et al. PromptCNER: A Segmentation-based Method for Few-shot Chinese NER with Prompt-tuning. ACM Transactions on Asian and Low-Resource Language Information Processing. 2025;24(9):1-24. doi:10.1145/3705314

BibTeX
@article{Mai2025,
  author = {Mai, Cheng-Cheng and Chen, Yu and Gong, Ziyu and Wang, Hanxiang and Qiu, Mengchuan and Yuan, Chunfeng and Huang, Yihua},
  title = {PromptCNER: A Segmentation-based Method for Few-shot Chinese NER with Prompt-tuning},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2025},
  volume = {24},
  number = {9},
  pages = {1--24},
  doi = {10.1145/3705314}
}
Kostenlos starten →