Entity-identification cooperative learning algorithm based on document type

Abstract

The invention discloses an entity-identification cooperative learning algorithm based on a document type, wherein the algorithm comprises a model building module and a model application. The model building module comprises text-type-based entity-identification classifier building and text classifier building. The model application comprises text type identification and text-type-based entity identification. In the algorithm, an integrated learning algorithm and a cooperative training algorithm are combined; meanwhile, in a data set pre-processing process, text-type-based data set segmentation is carried out, and the variety of data sets is considered. In a model building process, sparse labeled data is utilized as training data, and a plurality of basic algorithms are applied and are integrated by virtue of an integrated learning mode, so that the variety of the algorithms is considered. By combining multiple technologies, and considering the variety of algorithms and data sets, the entity-identification cooperative learning algorithm is guaranteed to obtain satisfying effect on an entity identification task.

Description

technical field [0001] The invention belongs to the field of computers, and more specifically relates to a document type-based entity recognition cooperative learning algorithm, which can well improve the accuracy of entity recognition. Background technique [0002] With the development of information industry, the scale of computer network is expanding day by day, and a large amount of information appears in front of people in the form of electronic documents. At the same time, in various companies and enterprises, a large amount of data is also accumulated in this form. Most of the potentially useful information in these data exists in unstructured form. The accumulation of these large amounts of free texts also poses challenges for the application of semantic technology in enterprise-level environments. Therefore, people urgently need some technology to process this information. Entity linking is attracting increasing attention as a technique capable of linking a word ...

AI Technical Summary

Problems solved by technology

This algorithm adopts the model of integrated learning. Although the diversity of the learner is considered, the same data set is used for each cycle training learner, and the diversity of the data set is not considered. This is a shortcoming of it.

[0006] Although the existing methods introduced above have all improved the accuracy of the labeling problem, they only consider one aspect, either considering the diversity of the data set and not the diversity of the algorithm, or considering the diversity of the algorithm Sex does not consider the diversity of data sets, and cannot meet the needs of both aspects

Images