Entity identification method, terminal equipment and storage medium

Abstract

The invention relates to an entity recognition method, terminal equipment and a storage medium. The method comprises the steps of S1, constructing a word graph containing domain entities correspondingto a to-be-recognized text; S2, expressing each word in the to-be-recognized text as a vocabulary tensor through a word vector embedding layer; S3, extracting candidate entities corresponding to theto-be-recognized text from the constructed word graph through a graph neural network module according to all vocabulary tensors of the to-be-recognized text, wherein the graph neural network module comprises a graph attention network layer and a bidirectional graph convolutional network layer; S4, converting a vocabulary tensor and a candidate entity of the text to be recognized into an intermediate calculation tensor containing context information through a bidirectional recurrent neural network layer; and S5, inputting the intermediate calculation tensor into a CRF decoding layer for decoding to obtain an entity contained in the finally recognized text to be recognized. According to the method, the secondary graph structure of the entity boundary is modeled, and the relationship betweenthe entity boundary and the graph neural network is analyzed, so that influence of insufficient judgment of the entity boundary on the result accuracy is reduced.

Description

Technical field[0001]The invention relates to the field of text recognition, in particular to an entity recognition method, terminal equipment and storage medium.Background technique[0002]Named Entity Recognition (NER), also known as "proprietary name recognition", refers to the recognition of entities with specific meanings in the text, including names of persons, places, organizations, proper nouns, etc. Simply put, it is to identify the boundaries and categories of entity references in natural text. The current entity recognition methods include:[0003]1. Supervised learning method: This type of algorithm needs to use large-scale labeled corpus to train the model parameters. Currently commonly used models or methods include hidden Markov model (HMM), language model, maximum entropy model, support tensor machine (SVM), decision tree (DT) and conditional random field (CRF). The current method based on conditional random field is the most successful method in named entity recognition...

AI Technical Summary

Problems solved by technology

[0009] 1. Existing entity recognition models based on recurrent neural networks require a large amount of high-quality labeled training data, and specific professional field scenarios usually lack high-quality labeled entities, which brings great challenges to existing model training

[0010] 2. The existing entity recognition model cannot handle nested entities well (such as entity: Xiamen Jimei Software Park, where Xiamen, Jimei, Software Park and Jimei Software Park are all independent entities). The usual practice is to take the most The outer (longest) entity, ignoring other entities that exist inside it

[0011] 3. The bottleneck of existing entity recognition technology lies in the insufficient accuracy of entity boundary determination

Usually sparse boundary labels and fuzzy matching will make the accuracy of entity recognition results unable to meet expectations

Images