Joint recommendation system based on joint learning framework

Abstract

The invention discloses a joint recommendation system based on a joint learning framework, which belongs to the technical field of joint recommendation systems and comprises a target domain input end, a main LSTM (Long Short Term Memory) layer, a main hidden layer, a merging layer, a main activation function layer, a source domain input end, an auxiliary LSTM layer, an auxiliary hidden layer, a joint hidden layer, an auxiliary activation function layer, an auxiliary task output end and a main task output end. The target domain input end receives related data predicted by a target domain, generates a corresponding main task according to the related data and sends the main task to the main LSTM layer, the main LSTM layer receives the main task and enables the main task to enter an LSTM network to participate in judgment of a word segmentation NER model, and meanwhile, the main LSTM layer generates a main hidden layer on the basis of the target domain. Through a joint learning method, the source field sample assists the target field to perform word segmentation, so that the sample labeling time is shortened, and the word segmentation performance can be improved at the same time.

Description

technical field [0001] The invention relates to the technical field of joint recommendation systems, in particular to a joint recommendation system based on a joint learning framework. Background technique [0002] Chinese NER entity recognition requires a large amount of corpus for model training, but in reality, the corpus data is lacking, requiring a lot of manpower and material resources for data annotation. [0003] Patent No. CN202010895913.X discloses a Chinese word segmentation and entity recognition joint learning method automatically generated by a data set, the method includes the following steps: the first step, the construction of the target domain data set; the second step, the first step The sentence s with a string of Chinese character sequences in the data set obtained in is input into the character vector representation layer of the neural network model, and the vector representation of each Chinese character is obtained; the third step, the Chinese charact...

AI Technical Summary

Problems solved by technology

[0006] However, the specific point of the text in the health field is that it is highly professional. If the model is directly used to train the NER model on the health report information in the health field, then labeling samples will consume a lot of manpower and material resources.

Images