Generation of Chinese classical poetry based on pre-trained model
Ziyao Wang, Lujin Guan, Guanyu Liu

TL;DR
This paper explores generating high-quality Chinese classical poetry using pre-trained models like BART, demonstrating that AI can produce poetry indistinguishable from human work and aiding modern poets' creativity.
Contribution
The study introduces FS2TEXT and RR2TEXT methods for style-specific poetry generation using pre-trained models, addressing relevance issues in AI poetry creation.
Findings
AI-generated poetry is indistinguishable from human poetry by experts
Proposed models successfully generate metrical and style-specific poetry
Over 600 poets participated in evaluating AI poetry quality
Abstract
In order to test whether artificial intelligence can create qualified classical poetry like humans, the author proposes a study of Chinese classical poetry generation based on a pre-trained model. This paper mainly tries to use BART and other pre training models, proposes FS2TEXT and RR2TEXT to generate metrical poetry text and even specific style poetry text, and solves the problem that the user's writing intention gradually reduces the relevance of the generated poetry text. In order to test the model's results, the authors selected ancient poets, by combining it with BART's poetic model work, developed a set of AI poetry Turing problems, it was reviewed by a group of poets and poetry writing researchers. There were more than 600 participants, and the final results showed that, high-level poetry lovers can't distinguish between AI activity and human activity, this indicates that the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Technology in Applications · Computational and Text Analysis Methods
MethodsMulti-Head Attention · Test · Linear Layer · Dense Connections · Layer Normalization · Byte Pair Encoding · Residual Connection · Dropout · Attention Is All You Need · Softmax
