语料库与近代西北水利档案的数智化应用方式探索  

Exploration of the Application of Corpus and Modern Northwest Water Conservancy Archives in Digital Intelligence

作　　者：潘威 徐娟 Pan Wei;Xu Juan(School of History and Archives,Yunnan University)

机构地区：[1]云南大学历史与档案学院,云南昆明650091

出　　处：《图书馆杂志》2024年第8期13-22,共10页Library Journal

基　　金：国家社会科学基金冷门绝学专项团队项目“近代中国西部边疆多语种水利史料整理与研究”(项目编号:23VJXT018);国家社会科学基金重大项目“中国西北水资源利用史研究”(批准号:23&ZD255)的研究成果之一。

摘　　要：民国时期,新疆、甘肃、宁夏三省进行了一定规模的水利建设,尤其是在抗战时期,西北成为“大后方”的背景下,三省出现了现代意义上的水政机构,进行了一系列的水利工程建设。在这一过程中,产生了大量的西北分省水利档案,这批档案绝大多数是民国时期新疆、甘肃、宁夏各省的水利委员会工作档案,具有较强的专业性,所面向的学者群体规模较小。这样的专业性档案特别需要语料库的支持,本研究在阐述语料库在近代西北水利档案管理和研究中的必要性的基础之上,设计并搭建了“近代西北地区水利档案”语料库,初步实现了针对该档案的智能化检索和知识挖掘。本研究以部分近代“宁夏水利委员会档案”为例,展示了该语料库在近代西北水利史研究中的巨大作用。During the Republic of China period,Xinjiang,Gansu,and Ningxia Provinces carried out a certain scale of water conservancy construction.Especially in the war period when the northwest region became the“big backyard”,there appeared the water administrations of modern sense in these three provinces.A series of water conservancy projects were carried out,and a large number of northwest subprovincial water conservancy files were produced.The vast majority of these files were the working files of the water conservancy committees of Xinjiang,Gansu and Ningxia Provinces back then,which were highly specialized and oriented to a smaller group of scholars.On the basis of elaborating the necessity of corpus technology in the management and research of modern water conservancy archives,this study designs and builds a corpus of“Republic of China Northwest Frontier Water Conservancy Archives”,and initially realizes the intelligent search and knowledge mining for the archives.Taking“Ningxia Water Conservancy Commission Archives”as an example,this study demonstrates the critical role of corpus in the study of modern water conservancy history of Northwest China.

关 键 词：语料库 近代西北 水利档案 词性标注 

分 类 号：G270.7[文化科学—档案学] TV21[水利工程—水文学及水资源]