Text entity detection method and system and related components

Abstract

The invention discloses a text entity detection method, and the method comprises the steps: carrying out the matching of each statement instance in a target statement through a seed entity set to obtain a matching result, and generating annotation data corresponding to the target statement according to the matching result; querying a statement instance matched with an unlabeled corpus word frequency table in the target statement, and modifying the labeled data according to a query result to obtain local labeled data; training a sequence annotation neural model by utilizing the local annotationdata; and performing sequence annotation on the unannotated corpus in the target statement by utilizing the trained sequence annotation neural model so as to obtain an entity set of the target statement. According to the method, high-quality entity mining can be realized on the premise of not being limited by the quality and the scale of the unlabeled corpus. The invention further discloses a text entity detection system, a computer readable storage medium and electronic equipment, which have the above beneficial effects.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a text entity detection method and system, a computer-readable storage medium and an electronic device. Background technique [0002] New homogeneous entity mining is an open-domain entity extraction technique. Different from the traditional named entity recognition technology, which is only aimed at the identification of some specific types of entities, the mining of new similar entities focuses more on the analysis of the set of seed entities composed of a given entity of any open category, using the technology of entity extraction from related open entities. More new entities that belong to the same category as the entities in the set are mined from the unlabeled corpus in the domain. For example, given a seed entity set containing country names such as {China, Germany}, the extraction system can mine other entities such as {Japan, France}. New similar entit...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, the neural model of deep learning sequence labeling is usually used to realize entity mining, but this method requires a large amount of high-quality manual labeling data as raw materials for training models, which is currently open Named entity recognition training resources for domain categories are still quite scarce, and effective entity extraction cannot be performed

Images