A method and device for automatically generating poetry

Abstract

The objective of the present invention is to provide a method and an apparatus for automatically generating a poem. The method comprises: acquiring a poem genre corresponding to a to-be-generated poem and a subject heading that is selected for each to-be-generated line in the to-be-generated poem; according to the poem genre, determining a poem model based on a concentration mechanism; according to the subject heading of the to-be-generated line and all historical reference lines that have been generated before the to-be-generated line is generated, generating the to-be-generated line by using the poem model; using the generated to-be-generated line as a historical reference poem; and repeating executing the operations of generating the to-be-generated line and using the generated to-be-generated line as the historical reference line, until generating the to-be-generated poem. Compared with the prior art, the subject heading is allocated for each to-be-generated line by the method, and the subject heading is involved in the generation process of the whole to-be-generated poem, and when generating each to-be-generated line, all generated lines in the to-be-generated poem are used to improve logical associations between lines and enhance usage experience of users.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a technology for automatically generating poetry. Background technique [0002] As an integral part of China's long and splendid classical literature, Chinese classical poetry has both the beauty of Chinese and the inspiration of art. According to a given subject heading, it is a very challenging technical problem to generate a fluent and natural poem that is related to the subject heading, meets the requirements of poetic rhythm, and is fluent and natural. [0003] Existing techniques for generating poetry are mainly based on statistical translation models. Specifically, in order to generate the first verse of the poem, first obtain words related to the input subject word, get a candidate list of words, then arrange and combine these words to filter out the candidate verses that meet the level, and then use the language model to score, select The sentence with the highest sc...

AI Technical Summary

Problems solved by technology

[0005] 1) The topic words are only used to generate the first poem, so the correlation between the whole poem and the topic words is difficult to guarantee;

[0006] 2) The subject headings must be in the specified thesaurus, and it is not possible to handle subject names that may not be in the thesaurus, such as names of people and places;

[0007] 3) When each poem is generated, only the information of the previous poem can be used, but the information of all the poems that have been generated before can not be used, so the logical correlation between the poems is not strong;

Images