Abstract
Recent progress in neural learning demonstrated that machines can do well in regularized tasks, e.g., the game of Go. However, artistic activities such as poem generation are still widely regarded as human’s special capability. In this paper, we demonstrate that a simple neural model can imitate human in some tasks of art generation. We particularly focus on traditional Chinese poetry, and show that machines can do as well as many contemporary poets and weakly pass the Feigenbaum Test, a variant of Turing test in professional domains.
Our method is based on an attention-based recurrent neural network, which accepts a set of keywords as the theme and generates poems by looking at each keyword during the generation. A number of techniques are proposed to improve the model, including character vector initialization, attention to input and hybrid-style training. Compared to existing poetry generation methods, our model can generate much more theme-consistent and semantic-rich poems.
Q. Wang and T. Luo—The first two authors contributed equally.
D. Wang—RM 1-303, FIT BLDG, Tsinghua University, Beijing (100084), P.R. China. This work was supported by the National Science Foundation of China (NSFC) under the project NO. 61371136, and the MESTDC PhD Foundation Project No. 20130002120011. It was also supported by Huilan Ltd. and FreeNeb.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
These experts are professors and their postgraduate students in the field of Chinese poetry research. Most of them are from the Chinese Academy of Social Sciences (CASS).
- 3.
- 4.
The author of RNNPG [22] could not find the SMT model in the reproduction, unfortunately.
- 5.
These experts were nominated by professors in the field of traditional Chinese poetry research.
- 6.
These experts again are mostly from CASS, part of them attended the previous test.
- 7.
The criterion is to fool people in more than 30% of the trials. Refer to https://en.wikipedia.org/wiki/Turing_test.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Chen, Y.: Jin Poetry Chronicle. Shanghai Chinese Classics Publishing House, Shanghai (2013)
Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Feigenbaum, E.A.: Some challenges and grand challenges for computational intelligence. J. ACM (JACM) 50(1), 32–40 (2003)
Han, W.: Study on the Liao, Jin and Yuan Poetry and Music Theory. China Social Sciences Press, Beijing (2015)
He, J., Zhou, M., Jiang, L.: Generating Chinese classical poems with statistical machine translation models. In: Twenty-Sixth AAAI Conference on Artificial Intelligence (2012)
Jiang, L., Zhou, M.: Generating Chinese couplets using a statistical MT approach. In: Proceedings of the 22nd International Conference on Computational Linguistics, vol. 1, pp. 377–384. Association for Computational Linguistics (2008)
Liu, W.: ShiXueHanYing (1735)
Manurung, R., Ritchie, G., Thompson, H.: Using genetic algorithms to create meaningful poetic text. J. Exp. Theor. Artif. Intell. 24(1), 43–64 (2012)
Mikolov, T., Karafiát, M., Burget, L., Cernockỳ, J., Khudanpur, S.: Recurrent neural network based language model. In: 11th Annual Conference of the International Speech Communication Association. INTERSPEECH 2010, Makuhari, 26–30 September 2010, pp. 1045–1048 (2010)
Netzer, Y., Gabay, D., Goldberg, Y., Elhadad, M.: Gaiku: generating haiku with word associations norms. In: Proceedings of the Workshop on Computational Approaches to Linguistic Creativity, pp. 32–39. Association for Computational Linguistics (2009)
Oliveira, H.: Automatic generation of poetry: an overview. Universidade de Coimbra (2009)
Oliveira, H.G.: PoeTryMe: a versatile platform for poetry generation. In: Proceedings of the ECAI 2012 Workshop on Computational Creativity, Concept Invention, and General Intelligence (2012)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, pp. 311–318. Association for Computational Linguistics (2002)
Tosa, N., Obara, H., Minoh, M.: Hitch haiku: an interactive supporting system for composing haiku poem. In: Stevens, S.M., Saldamarco, S.J. (eds.) ICEC 2008. LNCS, vol. 5309, pp. 209–216. Springer, Heidelberg (2008). doi:10.1007/978-3-540-89222-9_26
Wang, L.: A Summary of Rhyming Constraints of Chinese Poems (Shi Ci Ge Lv Gai Yao). Beijing Press, Beijing (2002)
Wang, Q., Luo, T., Wang, D., Xing, C.: Chinese song iambics generation with neural attention-based model. In: IJCAI 2016 (2016)
Wu, X., Tosa, N., Nakatsu, R.: New hitch haiku: an interactive renku poem composition supporting tool applied for sightseeing navigation system. In: Natkin, S., Dupire, J. (eds.) ICEC 2009. LNCS, vol. 5709, pp. 191–196. Springer, Heidelberg (2009). doi:10.1007/978-3-642-04052-8_19
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 Twenty-Third International Joint Conference on Artificial Intelligence, pp. 2197–2203. AAAI Press (2013)
Yoshikawa, K.: Gen Min shi gaisetsu. Iwanami Shoten Publishers, Tokyo (1963)
Zeiler, M.D.: AdaDelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 670–680 (2014)
Zhou, C.L., You, W., Ding, X.: Genetic algorithm and its implementation of automatic generation of Chinese songci. J. Softw. 21(3), 427–437 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Wang, Q., Luo, T., Wang, D. (2016). Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test. In: Liu, CL., Hussain, A., Luo, B., Tan, K., Zeng, Y., Zhang, Z. (eds) Advances in Brain Inspired Cognitive Systems. BICS 2016. Lecture Notes in Computer Science(), vol 10023. Springer, Cham. https://doi.org/10.1007/978-3-319-49685-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-49685-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49684-9
Online ISBN: 978-3-319-49685-6
eBook Packages: Computer ScienceComputer Science (R0)