Predicate recognition method and device and storage medium

Abstract

The invention discloses a predicate recognition method and device, and a storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining a plurality of first predicates corresponding to entity types contained in target text information; based on a first text matching model, obtaining semantic features of the target text information and semantic featuresof at least one piece of template text information corresponding to each first predicate, and according to the semantic feature of the at least one piece of template text information, obtaining the semantic feature of each first predicate, and according to the similarity between the target text information and the semantic feature of each first predicate, selecting a target predicate matched withthe target text information from the plurality of first predicates. Since the semantic feature of the first predicate is acquired according to the semantic feature of the at least one piece of template text information corresponding to the first predicate, the meaning of the first predicate can be expressed more accurately, the accuracy of the acquired semantic feature of the first predicate andthe accuracy of the determined similarity are improved, and the accuracy of the acquired target predicate is further improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a predicate recognition method, device and storage medium. Background technique [0002] Natural language includes entities and predicates. Entities refer to nouns with specific meanings, and predicates are words used to describe the relationship between entities. Predicates play an important role in understanding the meaning of text. For example, in an intelligent question answering system, the meaning of the question information can be prepared according to the predicates in the question information, so as to accurately determine the answer information corresponding to the question information. [0003] In related technologies, when the target text information is obtained, the target text information is analyzed to obtain the entity contained in the target text information, and then at least one predicate corresponding to the entity type of the entity is obtained t...

AI Technical Summary

Problems solved by technology

[0004] However, because the similarity between the text information and the predicate is determined only based on the semantic features of the text information and the semantic features of the predicate, the accuracy of the determined similarity is low, which in turn leads to the low accuracy of the determined predicate

Images