Abstract:In this paper

we proposed a novel automatictagging system which aimed at the lack of tags about digital resources and thedifficulty of extending tags This tagging system can effectively extend tagsfor public cultural resources we collected and other public data sets Thealgorithm of tagging system based on neural network and generative learning Weuse Latent Dirichlet Allocation (LDA) and Word2Vec to process resources andinitial tags

generating the representation vectors of resources and initialtags

then use these two kinds of vector to build this automatic tagging systemfocused on digital resources From the results

the Precision

MRR

MAP andother indexes of this method is better than other comparison tagging methodsmentioned in this paper

and it can solve the lack of tags in some casesIncreasing utilization of resources