引用功能感知的知识单元引用网络构建与多维分析

Construction and Multidimensional Analysis of a Citation Function-aware Knowledge Unit Citation Network

[目的/意义]针对知识单元引用网络中关联关系单一的局限,本文通过引用功能增强网络节点之间语义关联类型,提出一种引用功能感知的知识单元引用网络,并进行领域知识多维分析。[方法/过程]首先对学术文本进行解析,抽取文献间引用关系、引文上下文以及引用对象等信息,并对引用功能和引用对象进行自动识别。在此基础上,采用复杂网络图方法构建引用功能感知的知识单元引用网络,从网络结构分析与可视化、知识单元多维引用关联分析、知识群落分析3个方面进行领域知识多维分析,并以国际计算语言学协会会议论文数据集为例进行实证研究。[结果/结论]结果验证了本文所提出方法的有效性,发现了特定领域知识间使用、扩展和对比模式,丰富了知识群落的语义信息。本文扩展了知识单元引用网络的研究方法,深层次揭示了学科知识之间的语义关联,为学科知识结构分析提供了一种新的路径。

[Purpose/Significance]Aiming at the limitation of single associations in knowledge unit citation network,this paper enhances the semantic association types between network nodes through citation function,proposes a citation function-aware knowledge unit citation network,and conducts multi-dimensional analysis of domain knowledge.[Method/Process]Firstly,the academic text was parsed to extract information such as citation links,citation context and citation objects,and their citation functions were identified.On this basis,the complex network method was used to construct a citation function-aware knowledge unit citation network,and the multidimensional analysis of domain knowledge was carried out from the citation network structure and visualization,multidimensional citation relationship of knowledge units,and knowledge community.The proceedings of ACL(Association for Computational Linguistics)were used as an example for empirical research.[Result/Conclusion]The results verify the effectiveness of the proposed method,discover the usage,extension and comparison patterns among domain knowledge,and enrich the semantic information of knowledge communities.This study extends the research method of knowledge unit citation network,deeply reveals the semantic relationships between discipline knowledge,and provides a new path for analyzing discipline knowledge structure.