Wang Haifeng

TL;DR: In this article, a LSTM-based method was proposed to generate lyrics of the sentence to be generated and the length of each sentence in the source lyrics. But this method requires a large number of inputs to generate a sentence.

TL;DR: In this article, a poem forming keyword obtaining method and device based on artificial intelligence is proposed, which comprises the following steps: extracting one or more basic keywords from poem request information; obtaining one or several expansion keywords corresponding to the basic keywords if the basic keyword are not in a poem corpus database; selecting at least one expansion keyword contained in the poem corpus corpus database from the expansion keywords, and forming a corresponding verse according to the keyword.

TL;DR: In this article, a method and device for generating expansion query terms is presented. But the method is limited to one or more pieces of entity information, and needed relevant information corresponding to the one or multiple pieces of information is acquired; entity expansion information is determined according to the acquired entity information and the need relevant information of the entity information to be stored.

TL;DR: In this paper, a method for automatically generating poems was proposed, which includes steps of constructing state machines according to a plurality of preset rhythm rules; acquiring candidate word sets from candidate word libraries according to known poem associated information and the state machines; determining associated information of each candidate word in the candidate word set; generating the poems according to the candidate words, associated information, and preset scoring rules.