EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Coreference Resolution Based on High-Dimensional Multi-Scale Information

Yu Wang, Zenghui Ding, Tao Wang iD, Shu Xu, Xianjun Yang, Yining Sun

Entropy · 19.06.2024 · 26 (6) · 529

DOI: 10.3390/e26060529 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 19.06.2024. Verfasst von Yu Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Major Science and Technology Project, National Key Research and Development Program of China, The Natural Science Research Project of Anhui Province Higher Education Institutions.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coreference resolution is a key task in Natural Language Processing. It is difficult to evaluate the similarity of long-span texts, which makes text-level encoding somewhat challenging. This paper first compares the impact of commonly used methods to improve the global information collection ability of the model on the BERT encoding performance. Based on this, a multi-scale context information module is designed to improve the applicability of the BERT encoding model under different text spans. In addition, improving linear separability through dimension expansion. Finally, cross-entropy loss is used as the loss function. After adding BERT and span BERT to the module designed in this article, F1 increased by 0.5% and 0.2%, respectively.

Schlagwörter

Stichwörter der Autor:innen

BERTcoreference resolutioncross-entropy losshigh-dimensional featuresmulti-scale convolutionnatural language processing

Autor:innen und Institutionen

  • Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China.
  • Science Island Branch, Graduate School of USTC (University of Science and Technology of China), Hefei 230026, China.

ORCID-Profile: Tao Wang

Förderung

  • Anhui Provincial Major Science and Technology Project
  • National Key Research and Development Program of China
  • The Natural Science Research Project of Anhui Province Higher Education Institutions
  • Natural Science Research Project of Anhui Province Higher Education Institutions

Zitieren

APA

Wang, Y., Ding, Z., Wang, T., Xu, S., Yang, X., & Sun, Y. (2024). Coreference Resolution Based on High-Dimensional Multi-Scale Information. Entropy, 26(6), 529. https://doi.org/10.3390/e26060529

Vancouver

Wang Y, Ding Z, Wang T, Xu S, Yang X, Sun Y. Coreference Resolution Based on High-Dimensional Multi-Scale Information. Entropy. 2024;26(6):529. doi:10.3390/e26060529

BibTeX
@article{Wang2024,
  author = {Wang, Yu and Ding, Zenghui and Wang, Tao and Xu, Shu and Yang, Xianjun and Sun, Yining},
  title = {Coreference Resolution Based on High-Dimensional Multi-Scale Information},
  journal = {Entropy},
  year = {2024},
  volume = {26},
  number = {6},
  pages = {529},
  doi = {10.3390/e26060529}
}
Kostenlos starten →