A Radical-Based Token Representation Method for Enhancing Chinese Pre-Trained Language Models

Shranjeno v:

Bibliografske podrobnosti
izdano v:	Electronics vol. 14, no. 5 (2025), p. 1031
Glavni avtor:	Qin, Honglun
Drugi avtorji:	Li, Meiwen, Wang, Lin, Ge, Youming, Zhu, Junlong, Zheng, Ruijuan
Izdano:	MDPI AG
Teme:	Word processing Language Datasets Semantic features Deep learning Natural language processing Word boundaries Methods Phonetics Language modeling Chinese languages Morphology Representations Efficiency Semantics Experiments Personality Task performance Vocabulary
Online dostop:	Citation/Abstract Full Text + Graphics Full Text - PDF
Oznake:	Označite Brez oznak, prvi označite!

Komentirajte kot prvi!