Single-label text classification method, computing device, and computer-readable storage medium

Abstract

The present disclosure provides a single-label text classification method, a computing device and a computer-readable storage medium. The method includes: constructing a sample set based on user behavior data and commodity data, wherein the sample set includes a plurality of samples, and each sample includes a first field indicating text and a second field indicating a single label; Segment a field to obtain at least one feature word, and obtain a formatted sample of the sample based on the second field and the at least one feature word; train the first formatted sample based on the multiple formatted samples of the plurality of samples A neural network model; dividing the plurality of formatted samples into a plurality of groups based on the second field; and for each group, determining a second neural network model based on an average word vector of at least one feature word in the group. Using data from multiple sources to construct a large amount of training sample set and using a combined model reduces the performance loss of the online system.

Description

Technical field[0001]The present disclosure generally relates to the field of machine learning, and more specifically, to a single-label text classification method, computing device, and computer-readable storage medium.Background technique[0002]Currently, various machine learning-based methods have been proposed to classify objects such as text and pictures. These classification methods usually require a large amount of data to train the neural network model to classify various objects into multiple categories. However, in some cases, such as in e-commerce search scenarios, the text to be classified (search term) is usually single-label text, which often faces problems such as insufficient data volume and excessive data noise. Especially in scenarios such as system cold start, user behavior data is insufficient. Under these conditions, how to build an effective data set is the cornerstone of producing effective models and achieving accurate text classification.[0003]In addition, co...

AI Technical Summary

Problems solved by technology

[0003] In addition, conventional classification methods usually use a deep network model. Due to the deep network layer, complex structure, and various parameters, the deployment of the model online will cause a certain degree of performance loss. This part of the loss is sensitive to response time systems (such as search , recommendation system, etc.) can not be ignored

[0004] Furthermore, in the case of a small data volume, the single-model classification scheme makes the entire classification algorithm completely dependent on the quality of a single model, which lacks robustness

Images