Classical Chinese Poetry Generation based on Transformer-XL

Abstract

Classical Chinese poetry is a kind of formatted text with phonological patterns. It has been a big challenge for the classical Chinese poetry generation. Because deep learning technology has made great progress in image and text processing, we present a classical Chinese poetry generation model based on Transformer-XL that can capture longer-term dependency than the original transformer. Our model creates the first character according to the title specified by a user and then concatenates the generated character as the input to predict the next character until reaches the predefined number of characters. Experimental results show that our model can generate poems that have good format, consistency and rhythm.