Domain entity disambiguation method for fusing word vectors and topic model

Abstract

The invention relates to a domain entity disambiguation method for fusing word vectors and a topic model, and belongs to the technical field of natural language processing and deep learning. The method comprises the steps of obtaining candidate entity sets of to-be-disambiguated entities; obtaining vector forms of the to-be-disambiguated entities and candidate entities, obtaining categorical referents of the to-be-disambiguated entities in combination with a hyponymy relation domain knowledge base, and performing context similarity and categorical referent similarity calculation; performing word vector training on documents in different topic classifications by utilizing the LDA topic model and a Skip-gram word vector model, obtaining word vector representations of different meanings of apolysemous word, extracting a topic domain keyword of a text by using a K-Means algorithm, and performing domain topic keyword similarity calculation; and finally, fusing three feature similarities, and taking the candidate entity with the highest similarity as a final target entity. The method is superior to a conventional disambiguation method and can well meet the demands of actual applications.

Description

technical field [0001] The invention relates to a domain entity disambiguation method that combines word vectors and topic models, and belongs to the technical fields of natural language processing and deep learning. Background technique [0002] Entity disambiguation is one of the important tasks in the field of natural language processing. This task aims to eliminate semantic ambiguity by clarifying the meanings of polysemous words in the text, and provides help for humans and computers to better understand natural language information. The task of entity disambiguation For general texts, such as news, web pages, etc., Wanwang uses a corpus composed of texts in multiple fields. However, in practical applications, it is often necessary to disambiguate texts in a specific field. This is not only important for the mining of domain knowledge It is of great significance, and it is helpful to the construction of domain knowledge base, automatic translation of professional litera...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a domain entity disambiguation method that combines word vectors and topic models to solve the existing entity disambiguation method. Using the Skip-gram word vector calculation model can only calculate a mixed polysemous word when dealing with polysemous words. Semantic word vectors, unable to distinguish the different meanings of polysemous words

Images