Abstract
Poetry is a kind of literary art, which conveys emotion with aesthetic expressions. Poetry automatic generation is challenging because it is required to confirm the semantic representation (content) and metrical constraints (form). Most previous work lacks the effective use of metrical information, resulting in the generated poems may break these constraints, which are essential for poetry. In this paper, we formulate the poetry generation task as a constrained text generation problem. A Transformer-based dual-encoder model is then proposed to force the poetry generation conditioned on both the writing intention and the metrical patterns. We conduct experiments on three popular genres of Chinese classical poetry: quatrains (
), regulated verse (
) and Song iambic (
). Both automatic and human evaluation results confirm that our method (poetry generation with metrical constraints, MCPG) significantly improves metrical compliance of generated poems while maintaining coherence and fluency.
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
Similar content being viewed by others
Notes
- 1.
‘co’, ‘pe’ and ‘ca’ refer to the punctuation
respectively.
- 2.
Tone and Rhyme are defined by TongYun (a pioneering book on Chinese rhythm). Learn more at https://sou-yun.cn/mqr.aspx.
- 3.
- 4.
A pre-trained model for Chinese classical poetry, developed by Research Center for Natural Language Processing, Computational Humanities and Social Sciences, Tsinghua University. URL: https://github.com/THUNLP-AIPoet/BERT-CCPoem.
- 5.
A poem may have multiple groups of rhymes, especially Song iambic.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)
Bugliarello, E., Okazaki, N.: Enhancing machine translation with dependency-aware self-attention, pp. 1618–1627. Association for Computational Linguistics (2020)
Chen, H., Yi, X., Sun, M., Li, W., Yang, C., Guo, Z.: Sentiment-controllable Chinese poetry generation, pp. 4925–4931. ijcai.org (2019)
de Cruys, T.V.: Automatic poetry generation from prosaic text, pp. 2471–2480. Association for Computational Linguistics (2020)
Deng, L., et al.: An iterative polishing framework based on quality aware masked language model for Chinese poetry generation, pp. 7643–7650. AAAI Press (2020)
Gervás, P.: An expert system for the composition of formal Spanish poetry. Knowl. Based Syst. 14(3–4), 181–188 (2001)
He, J., Zhou, M., Jiang, L.: Generating Chinese classical poems with statistical machine translation models. In: AAAI (2012)
Jiang, L., Zhou, M.: Generating Chinese couplets using a statistical MT approach. In: COLING, pp. 377–384 (2008)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)
Kumar, A., Ahuja, K., Vadapalli, R., Talukdar, P.: Syntax-guided controlled generation of paraphrases. Trans. Assoc. Comput. Linguist. 8, 330–345 (2020)
Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models, pp. 110–119. The Association for Computational Linguistics (2016)
Li, J., et al.: Generating classical Chinese poems via conditional variational autoencoder and adversarial training, pp. 3890–3900. Association for Computational Linguistics (2018)
Li, P., Zhang, H., Liu, X., Shi, S.: Rigid formats controlled text generation, pp. 742–751. Association for Computational Linguistics (2020)
Liao, Y., Wang, Y., Liu, Q., Jiang, X.: GPT-based generation for classical Chinese poetry. CoRR arXiv:1907.00151 (2019)
Liu, D., Lv, J., Li, Y.: Generating style-specific Chinese tang poetry with a simple actor-critic model. IEEE Trans. Emerging Top. Comput. Intell. 3(4), 313–321 (2018)
Manurung, H.: An evolutionary algorithm approach to poetry generation (2004)
Peng, H., Parikh, A.P., Faruqui, M., Dhingra, B., Das, D.: Text generation with exemplar-based adaptive decoding, pp. 2555–2565. Association for Computational Linguistics (2019)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Su, H., et al.: Diversifying dialogue generation with non-conversational text, pp. 7087–7097. Association for Computational Linguistics (2020)
Vaswani, A., et al.: Attention is all you need, pp. 5998–6008 (2017)
Wang, Q., et al.: Learning deep transformer models for machine translation. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28 July–2 August 2019, Volume 1: Long Papers, pp. 1810–1822 (2019)
Wang, Q., Luo, T., Wang, D., Xing, C.: Chinese song iambics generation with neural attention-based model, pp. 2943–2949. IJCAI/AAAI Press (2016)
Wang, X., Pham, H., Yin, P., Neubig, G.: A tree-based decoder for neural machine translation, pp. 4772–4777. Association for Computational Linguistics (2018)
Wang, Z., et al.: Chinese poetry generation with planning based neural network. In: COLING, pp. 1051–1060 (2016)
Xiao, T., Zhu, J., Zhang, H., Li, Q.: NiuTrans: an open source toolkit for phrase-based and syntax-based machine translation. In: Proceedings of the ACL 2012 System Demonstrations, pp. 19–24 (2012)
Yan, R.: I, poet: automatic poetry composition through recurrent neural networks with iterative polishing schema. In: IJCAI, pp. 2238–2244 (2016)
Yan, R., Jiang, H., Lapata, M., Lin, S., Lv, X., Li, X.: I, poet: automatic Chinese poetry composition through a generative summarization framework under constrained optimization. In: IJCAI, pp. 2197–2203 (2013)
Yang, C., Sun, M., Yi, X., Li, W.: Stylistic Chinese poetry generation via unsupervised style disentanglement, pp. 3960–3969. Association for Computational Linguistics (2018)
Yang, X., Lin, X., Suo, S., Li, M.: Generating thematic Chinese poetry using conditional variational autoencoders with hybrid decoders, pp. 4539–4545. ijcai.org (2018)
Yi, X., Li, R., Yang, C., Li, W., Sun, M.: MixPoet: diverse poetry generation via learning controllable mixed latent space, pp. 9450–9457. AAAI Press (2020)
Yi, X., Sun, M., Li, R., Li, W.: Automatic poetry generation with mutual reinforcement learning, pp. 3143–3153. Association for Computational Linguistics (2018)
Yi, X., Sun, M., Li, R., Yang, Z.: Chinese poetry generation with a working memory model, pp. 4553–4559. ijcai.org (2018)
Zhang, J., et al.: Flexible and creative Chinese poetry generation using neural memory, pp. 1364–1373. Association for Computational Linguistics (2017)
Zhang, R., Liu, X., Chen, X., Hu, Z., Xu, Z., Mao, Y.: Generating Chinese CI with designated metrical structure, pp. 7459–7467. AAAI Press (2019)
Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks, pp. 670–680. ACL (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
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, Y. et al. (2021). Chinese Poetry Generation with Metrical Constraints. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)