A Study Of Classical Chinese Poetry Generation Based On Deep Learning Methods

The classical Chinese poetry is an important heritage of ancient Chinese culture.There are different kinds of Chinese classical poetry,such as Tang poetry and Song iambics.Each type of poetry has to follow some specific structural,rhythmical and tonal patterns.The generation of the Chinese poetry is a very challenging task in natural language processing.In this paper,we propose a planning based poetry generating method:the contents of poems("what to say")are first explicitly planned,and then surface realization("how to say")is conducted.Given a user's writing intent which can be a set of keywords,a sentence or even a document described by natural language,the first step is to determine a sequence of sub-topics for the poem using a poem planning model,with each line rep-resented by a sub-topic.The poem planning model decomposes the user's writing intent into a series of sub-topics,and each sub-topic is related to the main topic and represents an aspect of the writing intent.Then the poem is generated line by line,and each line is generated according to the corresponding sub-topic and the preceding generated lines,using a poem generation model.The poem generation model is modified from attention based encoder-decoder neural network model to support encoding of both sub-topics and the preceding lines.The contributions of our work are as follows:· First,we try to simulate the way of human thinking and propose a planning-based poetry generating framework that bring the planning idea into the poetry gen-eration.The poem generation model is modified from attention based encoder-decoder neural network to support encoding of sub-topics and preceding lines.· Second,we present practical methods to apply the planning-based poetry gener-ating framework to the specific poem generation tasks.· Third,we conduct an evaluation experiments which demonstrates that our pro-posed approach outperforms the state-of-the-art poetry generating methods and the poem quality is somehow comparable to human poets.