Scholars name disambiguation method based on heterogeneous network embedding

Abstract

The invention discloses a scholars name disambiguation method based on heterogeneous network embedding, which comprises the following steps of 1) setting a plurality of authors needing disambiguation,collecting all papers related to the authors needing disambiguation, and generating a paper relation heterogeneous network by utilizing the authors of the collected papers and semantic information ofthe papers; 2) according to the paper relation heterogeneous network, generating paths containing text information of neighbor nodes of paper nodes through a meta-path-based random walk strategy, andstoring the paths as a training corpus; 3) using Skip-gram to train the training corpus, and generating a paper representation vector corresponding to each paper; 4) for an author needing disambiguation in the step 1), obtaining a paper representation vector corresponding to the paper of the author from the obtained paper representation vector, and 5) clustering the paper representation vector obtained in the step 4) to obtain a plurality of clusters to realize disambiguation of the author name.

Description

technical field [0001] The invention relates to the technical fields of big data, knowledge graph, entity disambiguation, and heterogeneous network embedding, and specifically relates to a non-supervised method for learning the representation vector of heterogeneous network nodes based on meta-path random walk to disambiguate scholars' names. Background technique [0002] In building a knowledge base of scientific and technological literature, the problem of author name disambiguation is often encountered. For example, in the massive documents in the knowledge base, there will be a large number of authors with the same name, which will reduce the accuracy of name retrieval, character relationship mining, and character similarity association. For example, when retrieving an author's name, all the papers written by the author with the same name will appear. To solve this problem, clustering methods are usually used to divide these retrieved papers into different author entitie...

AI Technical Summary

Problems solved by technology

For example, in the massive documents in the knowledge base, there will be a large number of authors with the same name, which will reduce the accuracy of name retrieval, character relationship mining, and character similarity association

Images