How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks
This work addresses the novel task of visual inspiration for poetry generation, which has been rarely explored, offering potential cultural and artistic applications.
The paper tackles the problem of generating classical Chinese poetry from images, which is more challenging than from text due to rich visual information, and proposes a memory-based neural model that achieves accurate image conveyance as demonstrated by human evaluation and quantitative analysis.
With the recent advances of neural models and natural language processing, automatic generation of classical Chinese poetry has drawn significant attention due to its artistic and cultural value. Previous works mainly focus on generating poetry given keywords or other text information, while visual inspirations for poetry have been rarely explored. Generating poetry from images is much more challenging than generating poetry from text, since images contain very rich visual information which cannot be described completely using several keywords, and a good poem should convey the image accurately. In this paper, we propose a memory based neural model which exploits images to generate poems. Specifically, an Encoder-Decoder model with a topic memory network is proposed to generate classical Chinese poetry from images. To the best of our knowledge, this is the first work attempting to generate classical Chinese poetry from images with neural networks. A comprehensive experimental investigation with both human evaluation and quantitative analysis demonstrates that the proposed model can generate poems which convey images accurately.