A Data Augmentation Algorithm for Chinese Named Entity Recognition Based on Sequence Generative Adversarial Networks

Abstract

The present invention provides a method of selecting positive sample data in the source domain data to expand the training data of the target domain by fusing the semantic differences and label differences of the sentences in the source domain and the target domain, so as to enhance the named entity recognition performance of the target domain method. On the basis of the previous Bi‑LSTM+CRF model, in order to fuse the semantic difference and label difference of sentences in the source domain and the target domain, we introduce the semantic difference and label difference through the state representation and reward setting in reinforcement learning, so that the training The decision-making network can select sentences that have a positive impact on the performance of named entity recognition in the target domain in the data of the source domain, expand the training data of the target domain, solve the problem of insufficient training data in the target domain, and improve the named entity recognition of the target domain performance.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method of using a sequence generation confrontation network to enhance data and improve the performance of Chinese named entity recognition. Background technique [0002] In recent years, deep learning has made great progress in image, speech and natural language processing. As an emerging technology of machine learning algorithms, deep learning is motivated by the establishment of a neural network that simulates the human brain for analysis and learning. In the field of images, people use deep neural networks to realize target detection in images, such as combining convolutional neural networks with candidate windows to detect pedestrians in images; in the field of speech, deep learning is used for speech synthesis and recognition provide us with an intelligent voice system; in the field of natural language processing, deep learning is applied to various life scenarios, ...

AI Technical Summary

Problems solved by technology

[0015] 1. Although modifying the structure of the deep model can enhance the semantic representation of the text, it does not solve the problem of lacking a large amount of labeled data

[0016] 2. The introduction of external resources requires a lot of manpower and time to collect external resources, and it is necessary to design effective rules to add external resources to the model

Images