"六书"多模态处理的形声表征以完善汉语语言模型
Six-Writings multimodal processing with pictophonetic coding to enhance Chinese language models
李伟钢 1Mayara C.MARINHO 1Denise L.LI 2Vitor V.DEOLIVEIRA1
作者信息
- 1. 巴西利亚大学计算机科学系(CIC/UnB),巴西巴西利亚市,70910-900
- 2. 圣保罗大学经济管理会计审计学院(FEA/USP),巴西圣保罗市,05508-010
- 折叠
摘要
大型语言模型(LLMs)在自然语言处理中已取得显著成就,但在某些场景下,仍然面临解决中文语言处理复杂性的挑战.本文提出"六书"多模态处理(SWMP)框架,旨在考虑汉语形、声、音、像、意、会特性,便于中文语言多模态处理.在SWMP统一的理论框架下,提出"六书"形声编码(SWPC,简称"六书编码")方法,使得对汉字的表达既能与语法有机结合,又反映汉语灵活应用的特点.文中设计的实验场景包括:(1)实验性建立汉字字根、偏旁(形部)和部件(声部)的图像和"六书"编码(SWPC)的数据库,实现汉语文字和图形的双模态处理;(2)表征若干汉词生成机制,建立提示性问/答模式,进行类比推理.使用SWPC处理中文形态关系数据集(CA8-Mor-10177)的所有问题,精度可达100％.(3)建立"六书"形声编码对词嵌入生成结果微调机制.对中文单词相似度数据集(COS960)中39.37％的问题,相似度计算与人工基础评估结果的平均相对误差低于25％.这些优于目前同类基准精度的结果表明,"六书编码"尝试体现汉语细腻的局部表征和整体关联等特点,可作为对现行汉语语言处理理论和技术的有效补充.
Abstract
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
汉语语言模型/中文自然语言处理/生成式语言模型/多模态处理/六书Key words
Chinese language model/Chinese natural language processing(CNLP)/Generative language model/Multimodal processing/Six-Writings引用本文复制引用
基金项目
Brazilian National Council for Scientific and Technological Development(CNPq)(309545/2021-8)
出版年
2024
NETL
NSTL
万方数据