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

Spremljeno u:

Bibliografski detalji
Izdano u:	Electronics vol. 14, no. 5 (2025), p. 1031
Glavni autor:	Qin, Honglun
Daljnji autori:	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 pristup:	Citation/Abstract Full Text + Graphics Full Text - PDF
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!

Budi prvi tko komentira!