Generating Chinese Poems from Images Based on Neural Network

摘要

Chinese classical poetry generation from images is an overwhelmingly challenging work in the field of artificial intelligence. Inspired by recent advances in automatically generating description of an image and Chinese poem generation, in this paper, we present a generative model based on deep recurrent framework that describes images in the form of poems. Our model consists of two parts, one is to extract information according to the semantics presented in images, and the other is to generate each line of the poem incrementally according to the extracted semantic information from the images by a recurrent neural network. Experimental results thoroughly demonstrate the effectiveness of our approach by manual evaluation.