An Iterative Polishing Framework Based on Quality Aware Masked Language Model for Chinese Poetry Generation


  • Liming Deng Ping An Technology
  • Jie Wang Ping An Technology
  • Hangming Liang Ping An Technology
  • Hui Chen Ping An Technology
  • Zhiqiang Xie University of Science and Technology of China
  • Bojin Zhuang Ping An Technology
  • Shaojun Wang Ping An Technology
  • Jing Xiao Ping An Insurance (Group) Company of China



Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. In the first stage, an encoder-decoder structure is utilized to generate a poem draft. Afterwards, our proposed Quality-Aware Masked Language Model (QA-MLM) is employed to polish the draft towards higher quality in terms of linguistics and literalness. Based on a multi-task learning scheme, QA-MLM is able to determine whether polishing is needed based on the poem draft. Furthermore, QA-MLM is able to localize improper characters of the poem draft and substitute with newly predicted ones accordingly. Benefited from the masked language model structure, QA-MLM incorporates global context information into the polishing process, which can obtain more appropriate polishing results than the unidirectional sequential decoding. Moreover, the iterative polishing process will be terminated automatically when QA-MLM regards the processed poem as a qualified one. Both human and automatic evaluation have been conducted, and the results demonstrate that our approach is effective to improve the performance of encoder-decoder structure.




How to Cite

Deng, L., Wang, J., Liang, H., Chen, H., Xie, Z., Zhuang, B., Wang, S., & Xiao, J. (2020). An Iterative Polishing Framework Based on Quality Aware Masked Language Model for Chinese Poetry Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7643-7650.



AAAI Technical Track: Natural Language Processing