Knowledge graph construction method based on deep learning

Abstract

The invention relates to a knowledge graph construction method based on deep learning. The method comprises the steps that a target text statement is given, and a two-way long short term memory recurrent neural network model and a conditional random field model are used to recognize target entities in the target text statement; a context sensitive two-way long short term memory recurrent neural network model and a feedforward neural network model are used to extract the relation between every two target entities; a vector space model is used to normalize the target entities, and the normalized target entities are mapped to a concept; and a knowledge graph is constructed according to the target entities, the relation between the target entities and the concept. According to the method, the deep learning technology is applied to construction of the knowledge graph, entity recognition models of a two-way recurrent neural network and a conditional random field are adopted to recognize the target entities in the target text statement, feature engineering in the entity recognition process and the relation extraction process is reduced, the burden and trouble brought by manual design and feature adjustment are relieved, and knowledge in a text is mined precisely.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method for constructing a knowledge map based on deep learning. Background technique [0002] As a huge, open, heterogeneous and dynamic information container, the Web generates and accommodates a huge amount of text, data, multimedia, temporary data and other types of information. Due to scattered resources and no unified management and structure, it is not easy to obtain relevant information, and the content that people are really interested in is often submerged in a lot of irrelevant information. Only by conducting in-depth semantic mining of network content and understanding users' interests from the semantic level can we provide people with high-quality Internet information. In this context, search engine companies such as Google, Baidu, and Sogou have built knowledge graphs based on this. Knowledge graphs aim to describe various entities or ...

AI Technical Summary

Problems solved by technology

Feature-based models often need to design a large number of lexical, syntactic and semantic features, and then put them into classifiers such as support vector machines (SVM) for classification. The biggest problem with feature-based methods is that it takes a lot of time and time. Efforts to construct features

And another method based on kernel function, although there is no need to build a huge feature engineering, it is very difficult to design and choose a suitable kernel function

Images