Model training method and device

Abstract

The invention discloses a model training method and device, which can be used for determining a training sample containing any entity from each segment of text related to a target field based on each entity in a constructed knowledge base, and carrying out sequence labeling on each training sample according to the position of the entity in each training sample and the entity attribute of the entity. Then, the pre-trained language model is further trained through each training sample and the label thereof. According to the method, the training samples are determined on the basis of the entities in the constructed knowledge base, and the training samples are automatically labeled, so that the manual labeling cost is saved.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to a model training method and device. Background technique [0002] Knowledge graph is a graph data structure composed of nodes and edges, which is mainly used in the fields of intelligent question answering and information recommendation. Among them, each node in the knowledge graph represents an entity, and each edge represents the relationship between entities. [0003] At present, when constructing knowledge graphs in various fields, it is first necessary to obtain encyclopedia data in related fields, and perform knowledge mining on the obtained encyclopedia data to obtain relevant entity content and the relationship between entities. Finally, according to each entity and the relationship between them, the knowledge graph of the related field is constructed. [0004] Among them, a common knowledge mining method is based on machine learning or deep learn...

AI Technical Summary

Problems solved by technology

[0005] However, knowledge mining through machine learning models requires a large amount of manually labeled corpus data during model training, which requires high labor costs.

Images