Sequence labeling method and system, computer readable storage medium and computer equipment

Abstract

The invention discloses a sequence labeling method and system, a computer readable storage medium and computer equipment, and the sequence labeling method is based on a joint training mode, and specifically comprises the steps: a data processing step: labeling an original data text in a double-pointer mode, and obtaining a labeled data text; a sequence annotation model construction step: traininga dynamic pre-training model according to the annotation data text to obtain a sequence annotation model; and a sequence labeling step: labeling the real-time data text through the sequence labeling model. According to the method and the system, more accurate information can be obtained, and the model can be deduced according to the context of the entity, so that the problem of multiple meanings of one word can be solved, and the deducing speed is higher.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a joint training-based sequence labeling method, system, computer-readable storage medium and computer equipment. Background technique [0002] Named entity recognition (NER) is a very basic task in the fields of nlp, knowledge graph, etc. It aims to locate and classify named entities in text into pre-defined categories, such as people, organizations, locations, time expressions, quantities , currency value, percentage, etc. The effect of named entity recognition directly determines the effect of downstream tasks. [0003] In November 2018, the Google team released the pre-training model bert, which has achieved the best results in many tasks of nlp, and even surpassed human performance in some areas, but because bert uses a fixed mask mode and is relatively small The batch size is being trained, so the power of bert has yet to be further developed. In 2019, fa...

AI Technical Summary

Problems solved by technology

[0003] In November 2018, the Google team released the pre-training model bert, which has achieved the best results in many tasks of nlp, and even surpassed human performance in some areas, but because bert uses a fixed mask mode and is relatively small The batch size is being trained, so the power of bert has yet to be further developed

[0014] 1. For the form of thesaurus + rules, it is not sensitive to the discovery of new words, and its generalization ability to data is relatively low

[0015] 2. For the pipeline scheme of the encoder and decoder, due to the pipeline scheme, it is easy to cause the a

Images