Generating Chinese Classical Poems with RNN Encoder-Decoder

  • Xiaoyuan YiEmail author
  • Ruoyu Li
  • Maosong Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10565)


We take the generation of Chinese classical poetry as a sequence-to-sequence learning problem, and investigate the suitability of recurrent neural network (RNN) for poetry generation task by various qualitative analyses. Then we build a novel system based on the RNN Encoder-Decoder structure to generate quatrains (Jueju in Chinese), with a keyword as input. Our system can learn semantic meaning within a single sentence, semantic relevance among sentences in a poem, and the use of structural, rhythmical and tonal patterns jointly, without utilizing any constraint templates. Experimental results show that our system outperforms other competitive systems.


Chinese poetry generation Neural network Machine learning 


  1. 1.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the 2015 International Conference on Learning Representations, San Diego, CA (2015)Google Scholar
  2. 2.
    Cho, K., Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 1724–1734 (2014)Google Scholar
  3. 3.
    Gervás, P.: An expert system for the composition of formal Spanish poetry. In: Macintosh, A., Moulton, M., Coenen, F. (eds.) Applications and Innovations in Intelligent Systems VIII, pp. 19–32. Springer, London (2001). doi: 10.1007/978-1-4471-0275-5_2 CrossRefGoogle Scholar
  4. 4.
    He, J., Zhou, M., Jiang, L.: Generating chinese classical poems with statistical machine translation models. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence, Toronto, Canada, pp. 1650–1656 (2012)Google Scholar
  5. 5.
    Jiang, L., Zhou, M.: Generating chinese couplets using a statistical MT approach. In: Proceedings of the 22nd International Conference on Computational Linguistics, Manchester, UK, pp. 377–384 (2008)Google Scholar
  6. 6.
    Levy, R.P.: A computational model of poetic creativity with neural network as measure of adaptive fitness. In: Proceedings of the ICCBR-01 Workshop on Creative Systems (2001)Google Scholar
  7. 7.
    Manurung, H.M.: An evolutionary algorithm approach to poetry generation. Ph.D. thesis, University of Edinburgh (2003)Google Scholar
  8. 8.
    Sun, Z.: Three hundred Poems of the Tang Dynasty (Open image in new window) (1764)Google Scholar
  9. 9.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 4, 3104–3112 (2014)Google Scholar
  10. 10.
    van der Maaten, L.: Barnes-hut-SNE. In: Proceedings of the First International Conference on Learning Representations (ICLR 2013), Scottsdale, Arizona (2013)Google Scholar
  11. 11.
    Wu, X., Tosa, N., Nakatsu, R.: New hitch haiku: an interactive renku poem composition supporting tool applied for sightseeing navigation system. In: Proceedings of the 8th International Conference on Entertainment Computing, Paris, France, pp. 191–196 (2009)Google Scholar
  12. 12.
    Yan, R., Jiang, H., Lapata, M., Lin, S.-D., Lv, X., Li, X.: I, poet: automatic chinese poetry composition through a generative summarization framework under constrained optimization. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, pp. 2197–2203 (2013)Google Scholar
  13. 13.
    Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 670–680 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations