文献信息视阈下面向智慧服务的语料库构建研究

Research on the Construction of Smart Service Oriented Corpus from the Perspective of Literature Information

[目的/意义]在重视实证研究的大数据环境下,语料库作为一种定量研究方法,在语言研究、统计分析及机器学习等领域发挥了重要的作用;近年来,随着大量文献的文本化,语料库的构建不但会使文献信息的研究科学化、多样化,还会使文献信息服务精准化、智慧化。[方法/过程]文章在现有语料库研究的基础上,结合图书馆、情报与文献学的相关理论,把文献信息作为研究对象,为社会提供智慧服务为目标,提出了一种在文献信息视阈下面向智慧服务语料库构建的思路。[结果/结论]阐述文献信息视阈下语料库建设的过程,并描述了在智慧推送、智能分类、远距离阅读等领域推动智慧服务的应用场景。

[Purpose/significance] Emphasis on Empirical Research in the Big Data Environment, As a quantitative research method, corpus plays an important role in language research , statistical analysis, machine learning and artificial intelligence. In recent years, with the textualization of a large number of documents, the construction of corpus will not only make the research of document information more scientific and diversified, but also make the information service more accurate and intelligent.[Method/ process] On the basis of the existing corpus research and the related theories of library, information and philology, this paper takes document information as the research object and aims at providing smart service to the society. It puts forward a new idea of constructing a corpus of smart service from the perspective of document information.[Result/conclusion] This paper describes the process of building a corpus from the perspective of document information, and describes the application scenarios of promoting smart services in the fields of intelligent push, intelligent classification and distant reading.