基于古代绘画的古诗自动生成方法

Automatic Poetry Generation Based on Ancient Chinese Paintings

中国题画诗是世界艺术史上一种极为特殊的艺术形式,它结合了中国古代文学和美术,诗与画相得益彰、浑然一体.为实现计算机为画题诗的功能,提取和使用古代绘画的多句现代文描述,提高古诗对绘画的文学表达能力,提出一种基于古代绘画的古诗自动生成方法.首先根据古画建立多句现代文标注数据集,然后通过改进的图像描述方法提取古画语义特征得到多句现代文描述,最后通过双向LSTM编解码框架将这些现代文描述转化为律诗.针对宋代小品画的实验表明,所提方法生成的古诗前后连贯、押韵规律,符合古画原有的内容且符合上下文语境;用户调查评估结果表明了该方法的有效性,其内容一致性和总体满意度等指标均优于基于关键词的方法.

The Chinese painting poem is a very special art form in the history of world art.It combines ancient Chinese literature and fine arts,complements each other and blends together.In order to obtain computer-based painting poetry,an automatic poetry generation is proposed based on ancient Chinese paintings.It extracts multiple sentences from ancient paintings,which improves the literary expression ability of ancient poems in paintings.Firstly,a multi-sentence annotation data set for ancient paintings is established,and then semantic features of ancient paintings are extracted through an improved image captioning method.Finally,these modern text descriptions are converted into a four-character poem through a two-way LSTM encoding and decoding framework.The experiment on the paintings of the Song Dynasty demonstrates that the coherent and prosodic poems generated by our method are consistent with the original content and context of the ancient paintings.User study shows that the content consistency and user satisfaction of our method are better than keyword-based methods,which proves the validity of the proposed method。