Recognition method, device and electronic equipment for nested entity data

Abstract

The application discloses a nested entity data identification method, device and electronic equipment, and relates to the technical field of data identification. The method includes: arranging and combining the seed entity vocabulary of different entity categories to generate a short text data set; defining at least one entity category label for the short text in the short text data set, and corresponding to each entity category label in the short text Index information of the start and end of the subtext; use the defined short text dataset as the training set to train the recognition model of deep learning; use the trained recognition model to recognize nested entity data. This application adopts the method of starting and ending index + entity category label for sentences to define entity labeling information, which makes the realization of multi-nested entity content labeling easier, optimizes the process and workload of nested entity recognition for labeling, and saves Time cost and labor cost, which in turn can improve the recognition efficiency and accuracy of nested entity data.

Description

technical field [0001] The present application relates to the technical field of data identification, in particular to an identification method, device and electronic equipment for nested entity data. Background technique [0002] Named Entity Recognition (NER) is an important research direction in the field of natural language processing. It refers to the recognition of entities with specific meaning in text, mainly including names of people, places, institutions, and proper nouns. With the development of deep learning technology and the needs of actual production applications, the requirements for named entity recognition are also increasing. When using entities for search support, fine-grained and nested entity information is required to ensure the accuracy and coverage of searches. At this stage, the main technology used for named entity recognition is deep learning technology. [0003] When using deep learning technology for entity recognition, a large amount of labele...

AI Technical Summary

Problems solved by technology

[0004] However, this type of entity data labeling method is difficult to divide the granularity of entities, and multi-level BIO labeling requires a lot of time and labor costs. It is difficult to process a large amount of effective labeling data in a short period of time, which will affect the identification of nested entity data. efficiency and accuracy

Images