xscsdk

Quick Entry

标准当期目录
标准过刊浏览
标准优先出版
标准模板最新

Latest Articles
Online First
Archive

2024年 25卷第1期

Special Issue on Recent Advances in Artificial Intelligence Generated Content (AIGC)

ChatGPT: potential, prospects, and limitations AI导读

“The latest research in the field of artificial intelligence has made significant strides. Expert Li Wei explored the topic of deep learning, which provides solutions to address the challenges of AI development and opens up a new direction for research in this area.”

Jie ZHOU,Pei KE,Xipeng QIU,Minlie HUANG,Junping ZHANG

DOI：10.1631/FITEE.2300089

78

|

7

|

0

<HTML>
<L-PDF><XML><Meta-XML>

<引用本文> <批量引用> 55185868 false

更新时间：2024-07-11
Six-Writings multimodal processing with pictophonetic coding to enhance Chinese language models AI导读

“In the realm of natural language processing, the Six-Writings multimodal processing (SWMP) framework has been introduced to tackle the complexities of the Chinese language. The Six-Writings pictophonetic coding (SWPC) component effectively represents Chinese characters and words, facilitating dual-mode processing and matrix generation. Expert experiments have achieved 100% accuracy in Chinese morphological data set responses and refined word embedding results with an average relative error of ≤25%. This advancement lays a promising foundation for enhancing Chinese NLP efficiency.”

Li WEIGANG,Mayara Chew MARINHO,Denise Leyi LI,Vitor Vasconcelos DE OLIVEIRA

DOI：10.1631/FITEE.2300384

摘要：While large language models (LLMs) have made significant strides in natural language processing (NLP), they continue to face challenges in adequately addressing the intricacies of the Chinese language in certain scenarios. We propose a framework called Six-Writings multimodal processing (SWMP) to enable direct integration of Chinese NLP (CNLP) with morphological and semantic elements. The first part of SWMP, known as Six-Writings pictophonetic coding (SWPC), is introduced with a suitable level of granularity for radicals and components, enabling effective representation of Chinese characters and words. We conduct several experimental scenarios, including the following: (1) We establish an experimental database consisting of images and SWPC for Chinese characters, enabling dual-mode processing and matrix generation for CNLP. (2) We characterize various generative modes of Chinese words, such as thousands of Chinese idioms, used as question-and-answer (Q&A) prompt functions, facilitating analogies by SWPC. The experiments achieve 100% accuracy in answering all questions in the Chinese morphological data set (CA8-Mor-10177). (3) A fine-tuning mechanism is proposed to refine word embedding results using SWPC, resulting in an average relative error of ≤25% for 39.37% of the questions in the Chinese wOrd Similarity data set (COS960). The results demonstrate that SWMP/SWPC methods effectively capture the distinctive features of Chinese and offer a promising mechanism to enhance CNLP with better efficiency.
关键词：Chinese language model;Chinese natural language processing (CNLP);Generative language model;Multimodal processing;Six-Writings

155

|

6

|

0

<HTML>
<L-PDF><XML><Meta-XML>

<引用本文> <批量引用> 55185908 false

更新时间：2024-07-11