Multi-task classification model training method and device and multi-task classification method and device

Abstract

The invention provides a multi-task classification model training method and device, and a multi-task classification method and device. The multi-task classification model training method comprises the following steps: inputting preset information into a pre-training model, wherein the preset information comprises a plurality of information units; calling a parameter sharing layer, performing global vector representation processing on each information unit, and determining a global semantic representation vector of each information unit; calling a plurality of classifiers, performing classification processing on the preset information according to each global semantic representation vector, and determining a classification prediction result of the preset information; based on the classification prediction result, the first quantity, the second quantity and the labeling result, calculating to obtain a loss value; and under the condition that the loss value is within a preset range, taking a target pre-training model obtained by training as a multi-task classification model. According to the multi-task classification model training method, a good multi-task classification model can be obtained on the basis of a small amount of training data, and only a small amount of annotation training data needs to be added under the condition that a new task exists, and the annotation cost can be reduced.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of multi-task classification model training, and in particular, to a multi-task classification model training method, a multi-task classification method and a device. Background technique [0002] With the rapid development of e-commerce, more and more consumers post product reviews on Internet platforms. In the face of more direct feedback from users, how to integrate feedback information and respond quickly has become a major challenge for enterprises. For example, taking a restaurant as an example, the user review text may contain evaluation content on multiple dimensions such as merchant service, meal taste, and price level. In the advanced technology solution, natural language processing technology is usually used to mine the user's emotional tendency towards various dimensions of the merchant from the user comment text, which has important business value for O2O (Online to Offli...

AI Technical Summary

Problems solved by technology

[0004] Using the above method, it relies heavily on labeled data, especially the deep learning

Images