Entity recognition method, model training method and device

Abstract

The invention provides an entity recognition method and device and a model training method and device. The entity recognition method comprises the steps: obtaining a to-be-recognized text and a pre-trained entity recognition model, inputting the to-be-recognized text into a first sub-model and a second sub-model of the entity recognition model, obtaining a first word feature vector and a second word feature vector, inputting the first word feature vector and the second word feature vector into a third sub-model of the entity recognition model, obtaining a plurality of first hidden states and a plurality of second hidden states through bidirectional hidden state extraction of the third sub-model, splicing the plurality of first hidden states and the plurality of second hidden states to obtain a spliced hidden state, and inputting the spliced hidden state into a classification layer of the entity recognition model, and obtaining an entity recognition result of the to-be-recognized text through classification and recognition of the classification layer. During entity recognition, both grammatical semantics and lexical methods are considered, so that the recognition precision of the long entity is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence of computer technology, in particular to an entity recognition method. The present application also relates to an entity recognition model training method, an entity recognition device, an entity recognition model training device, a computing device, and a computer-readable storage medium. Background technique [0002] Artificial Intelligence (AI) refers to the ability of an engineered (that is, designed and manufactured) system to perceive the environment, as well as the ability to acquire, process, apply and represent knowledge. The development status of key technologies in the field of artificial intelligence, including machine learning, knowledge graphs, natural language processing, computer vision, human-computer interaction, biometrics, virtual reality / augmented reality and other key technologies. Natural Language Processing (Natural Language Processing) refers to the use of...

AI Technical Summary

Problems solved by technology

[0005] However, since the BERT model only has a strong comprehension ability at the grammatical and semantic levels, for long entities, the recognition accuracy will decrease. For example, for the long entity "Stanford University in California", it is easy to be recognized as an organization ( ORG, Organization) entity, but should actually be recognized as the location (LOC, Location) entity "California" with the ORG entity "Stanford University"

Images