Joint training method and device for entity recognition and entity disambiguation and medium

Abstract

The invention discloses a joint training method and device for entity recognition and entity disambiguation and a medium, and the method comprises the steps: carrying out the named entity recognitionof a text based on an entity recognition model, and obtaining a to-be-disambiguated entity; in the constructed knowledge base, performing entity mapping of the entities to be disambiguated, and obtaining candidate entities used for entity disambiguation; inputting the entity to be disambiguated and the candidate entity into an entity disambiguation model for entity prediction to obtain a disambiguation entity, and adjusting a first parameter of the entity disambiguation model according to the disambiguation entity; feeding back the disambiguation entity to the entity recognition model throughan entity attention mechanism layer additionally arranged in the entity recognition model, and adjusting a second parameter of the entity recognition model according to the disambiguation entity; andwhen the first parameter and the second parameter enable the sum of the loss values of the first loss function and the second loss function to meet the minimization condition, completing the joint training. By adopting the method and the device, the problem of low accuracy of entity identification and entity disambiguation in single-model learning in the prior art is solved.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to a joint training method, device and medium for entity recognition and entity disambiguation. Background technique [0002] In the era of big text data, massive amounts of text are yet to be utilized. In the field of natural language processing, we allow machines to learn the semantic knowledge of the text by mining the semantic information contained in the text, so as to understand the text content. In this process, identifying entities (mentions) in the text, such as person names, place names, and organizational structures, and disambiguating entities to eliminate ambiguity in text sentences is an important step for machines to understand text content. [0003] At present, based on single model learning, in the entity recognition stage, many manual operations are added to discover potential entities in the text, and the entities to be disambiguated in the text are...

AI Technical Summary

Problems solved by technology

[0005] Various embodiments of the present invention provide a joint training method, device, and medium for entity recognition and entity disambiguation to solve the problem of low accuracy in entity recognition and entity disambiguation in single-model learning in the related art

Images