Cross-language multi-source vertical domain knowledge graph construction method

Abstract

The invention discloses a cross-language multi-source vertical domain knowledge graph construction method, and relates to the technical field of knowledge engineering. According to the technical scheme, the method comprises the steps that vertical domain translation completes parallel corpus construction through content and link analysis according to input cross-language texts, domain dictionaries, domain term libraries, domain materials and data, and automatic translation of foreign language texts is achieved based on a trained translation model on the basis of preprocessing; domain knowledgepre-annotation training realizes active learning annotation based on text word segmentation and text clustering, to-be-annotated corpus screening based on an analysis topic is completed, and a confirmed service annotation data set is generated; an optimal algorithm is selected, and semantic feature extraction and entity relationship extraction are completed based on deep learning in combination with vertical domain translation data and an actual scene; and domain knowledge fusion and disambiguation are performed on knowledge from different sources through network equivalent entity combination, so that the cross-language multi-source vertical domain knowledge graph can be obtained.

Description

technical field [0001] The invention relates to the construction of cross-language knowledge graphs in the field of knowledge engineering technology, in particular to a method for constructing cross-language multi-source vertical domain knowledge graphs. Background technique [0002] Knowledge Graph originates from related academic research fields such as semantic web and graph database. Different fields have different emphasis on knowledge graph research, such as natural language processing, knowledge engineering, machine learning, database and data management. Different research and application. The construction of knowledge graph first needs to determine the available data sources, such as structured data, machine-readable open ontology or dictionary, open link data and open knowledge base, industry knowledge base and industry vertical website, online encyclopedia (wiki, interactive, Baidu) and data such as text. Then, effectively collect data, such as open link data co...

AI Technical Summary

Problems solved by technology

[0007] To sum up, the existing knowledge graphs mainly involve open domains, single data sources, and are mainly single-language graphs; knowledge graphs related to vertical fields are mainly concentrated in the financial field, and most of their data are structured texts; knowledge graphs have great potential in the field of public security. Potential application value, there is currently no relevant cross-language multi-source vertical domain knowledge map construction method

Images