A Computational Method for Entity Classification in Knowledge Base Based on Representation Learning

Abstract

The invention relates to a representation learning-based knowledge base entity classification calculation apparatus, and relates to the field of text classification and knowledge base complementation.The method comprises the steps of for entities in a knowledge base, constructing a co-occurrence network containing information of different levels, and coding co-occurrence information between wordsand words, between the entities and the words, between categories and the words and between the entities and the categories to the network; based on the constructed co-occurrence network, learning vector representation of the entities and the categories by utilizing a network-based representation learning method; based on the learnt vector representation, learning a mapping matrix for the entities and the categories by utilizing a learning sorting algorithm, wherein the semantically related entities and categories are approximate in a semantic space; and by utilizing a top-bottom search method, automatically allocating the categories to the entities in the knowledge base, and obtaining a path of a category. The method is in favor of solving the problem existent in an existing entity classification method.

Description

technical field [0001] The invention relates to the technical field of text classification and knowledge base completion, in particular to a calculation method for knowledge base entity classification based on representation learning. Background technique [0002] This section introduces readers to background technologies that may be related to various aspects of the present invention, and it is believed that useful background information can be provided to readers, thereby helping readers to better understand various aspects of the present invention. Accordingly, it is to be understood that the descriptions in this section are for the purposes stated above and do not constitute admissions of prior art. [0003] Knowledge bases have attracted increasing research interest in recent years. Most of the existing knowledge bases are not perfect, and many researchers are committed to the completion of the knowledge base. Assigning categories to entities in a knowledge base is an...

AI Technical Summary

Problems solved by technology

[0005] However, existing entity classification algorithms face two main problems: first, it is difficult to design effective features for entities in the knowledge base, which are different from entities appearing in the context, and contain less semantic information. Containing rich text information and structured information, it is necessary to represent the entities in the knowledge base in a reasonable way; second, the hierarchical relationship between categories is not fully considered, and the categories in the knowledge base form a tree structure, which implies With the corresponding structural information, the existing methods do not fully consider the hierarchical structure of the classification tree

Images