Classification result correction method, system, equipment and medium

Abstract

The invention discloses a classification result correction method. The method comprises the following steps: constructing a data set and labeling a classification label of a corresponding category for each piece of data in the data set; inputting each piece of data in the data set into the trained model to obtain the probability of the corresponding classification label, and calculating a correction matrix by using the classification label probability corresponding to each piece of data; expanding the classification labels of each category into a plurality of sub-labels; adjusting the output of the trained model to the probability of a plurality of sub-tags corresponding to each category; inputting to-be-classified data into the trained model to obtain the probability of a plurality of sub-tags corresponding to each category; and determining the final category of the to-be-classified data by using the probability of the plurality of sub-tags corresponding to each category and the correction matrix. The invention further discloses a system, computer equipment and a readable storage medium. According to the scheme provided by the invention, the labels are expanded, so that bias caused by different occurrence frequencies of the labels is eliminated.

Description

technical field [0001] The invention relates to the field of classification, in particular to a classification result correction method, system, equipment and storage medium. Background technique [0002] The core capabilities of the massive model are zero-sample learning and small-sample learning. That is, when faced with different application tasks, there is no need to retrain the model. However, the huge amount of models will bring bias from the corpus during pre-training, resulting in low accuracy or unstable performance of downstream tasks. The current solution is to compensate the biased label words through text-free input, calibrate them to an unbiased state, and reduce the difference between different prompt choices. However, due to the difference in the frequency of tags appearing in the pre-training corpus, the model will have a preference for the prediction results, that is, the model output accuracy is low. Therefore, the existing correction methods can only c...

AI Technical Summary

Problems solved by technology

However, due to the difference in the frequency of labels in the pre-training corpus, the model will have a preference for the prediction results, that is, the model output accuracy is low

Therefore, the existing correction methods can only correct the bias of the model to the label, and cannot correct the bias caused by the input sample.

Images