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:
Online pristup:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!
Opis
Sažetak:In the domain of natural language processing (NLP), a primary challenge pertains to the process of Chinese tokenization, which remains challenging due to the lack of explicit word boundaries in written Chinese. The existing tokenization methods often treat each Chinese character as an indivisible unit, neglecting the finer semantic features embedded in the characters, such as radicals. To tackle this issue, we propose a novel token representation method that integrates radical-based features into the process. The proposed method extends the vocabulary to include both radicals and original character tokens, enabling a more granular understanding of Chinese text. We also conduct experiments on seven datasets covering multiple Chinese natural language processing tasks. The results show that our method significantly improves model performance on downstream tasks. Specifically, the accuracy of BERT on the BQ Croups dataset was enhanced to 86.95%, showing an improvement of 1.65% over the baseline. Additionally, the BERT-wwm performance demonstrated a 1.28% enhancement, suggesting that the incorporation of fine-grained radical features offers a more efficacious solution for Chinese tokenization and paves the way for future research in Chinese text processing.
ISSN:2079-9292
Digitalni identifikator objekta:10.3390/electronics14051031
Izvor:Advanced Technologies & Aerospace Database