Domain event graph construction method and device fusing multiple types of facts and entity knowledge

Abstract

The invention relates to a domain event graph construction method and device fusing multiple types of facts and entity knowledge. The method comprises the following steps: performing cause relationship extraction and instance cause element extraction on a domain corpus to form an instance cause logic knowledge base; constructing an abstract concept knowledge base with hierarchy; performing entityword abstraction and predicate abstraction on instance events in the instance cause logic knowledge base by utilizing the abstract concept knowledge base to form an abstract cause graph; carrying outentity linking on instance events in the instance cause logic knowledge base by utilizing the entity knowledge graph and adopting an entity linking technology, and fusing event knowledge and entity knowledge to form a cause knowledge graph; and combining the abstract factorial map with the factorial knowledge map to form a domain event map. The advantages of static entity knowledge and action event knowledge can be integrated, the application range of knowledge questions and answers can be widened, and the domain event graph can be used as a common knowledge base to expand domain language resources.

Description

technical field [0001] The invention relates to a method and device for constructing a domain event map that integrates multiple types of affairs and entity knowledge, belongs to the fields of natural language processing and knowledge engineering, and belongs to a method for constructing a domain knowledge base. Background technique [0002] At present, the logic map with "events" as the core to describe the logical evolution relationship between events is receiving widespread attention. On the one hand, this type of map focuses on the transfer of spatial and temporal semantic states between events, and can express a A stronger and more direct correlation than correlation semantics; on the other hand, the knowledge bearing capacity is stronger, the action in the event has associated nominal subject and nominal object, and the nominal subject and object itself has rich entity knowledge information. The characteristics of these two aspects determine that the event map can sup...

AI Technical Summary

Problems solved by technology

[0006] 2. The event element extraction in event extraction often needs to preset the element category in advance, which is not conducive to the construction of a knowledge base for large-scale event representation. It is necessary to propose an acceptable and semantically rich event general argument

[0007] 3. The relationship extraction in event extraction is currently mainly concentrated in the two types of causal and sequential, and there is a lack of extraction attempts and application point exploration for other types

[0008] 4. The work on the integration and linking of event knowledge and substantive knowledge is still relatively blank

Images