Abstract
Creating and evaluating Chinese poems is challenging for learners. To address this, we propose an auto-generation model and evaluation system to assist learners in poem creation and provide feedback on constraint adherence. We conducted a user experiment with 16 participants and generated up to 100 poems per keyword using 29 random keywords. The proposed system significantly improved poem completeness and usability, but did not enhance creation satisfaction. Users found it easy to confirm adherence to poem rules, but that verifying rhymes presented difficulties. The participants expressed overall satisfaction with the process, and the poems created were perceived as fluent and thematically consistent. However, limitations in keyword usage hinder emotional expression. This study highlights the need to overcome these challenges in order to facilitate learners’ creation and evaluation of Chinese poems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chinese converter (Python). https://pypinyin.readthedocs.io/zh_CN/master/
Chinese new rhyme. https://en.wikipedia.org/wiki/Middle_Chinese
Ping Shui Rhyme (in Chinese). Baidu Baike. https://baike.baidu.com/item/%E5%B9%B3%E6%B0%B4%E9%9F%B5/2271158
uer/gpt2-chinese-cluecorpussmall. https://huggingface.co/uer/gpt2-chinese-cluecorpussmall/tree/main
Upper secondary school curriculum guideline 2018–03 notification (in Japanese) (2022). https://www.mext.go.jp/content/20230120-mxt_kyoiku02-100002604_03.pdf
Ariga, Y.: Sorin Chinese Poetry Composition Lecture Introductory Edition (in Japanese). Kokusho Publishing Association (1995)
Ariga, Y.: Sorin Chinese Poetry Composition Lecture Vocabulary (in Japanese). Kokusho Publishing Association (1995)
Attridge, D.: Poetic Rhythm: An Introduction. Cambridge University Press, Cambridge (1977)
Du, Z.: GPT2-Chinese: tools for training GPT2 model in Chinese language. GitHub (2019). https://github.com/Morizeyao/GPT2-Chinese
Hirata, K., Yokoyama, S., Yamashita, T., Kawamura, H.: Haiku generation using language model by transformer and its evaluation (in Japanese). Information Processing Society of Japan/Information Fundamentals and Access Technologies 2021-IFAT-143(2), 1–6 (2021)
Iritani, S.: Introduction to Chinese Poetry (in Japanese). Chunichi Publishing Company (1979)
Ishida, K.: On the knowledge obtain method of Chinese poem by its correcton software (in Japanese). Jpn. Soc. Artif. Intell. JSAI05, 104–104 (2005). https://doi.org/10.11517/pjsai.JSAI05.0.104.0
Ishida, K.: On a web service site for the correction of Chinese poems (in Japanese). Jpn. Soc. Artif. Intell. JSAI06, 157–157 (2006). https://doi.org/10.11517/pjsai.JSAI06.0.157.0
Kawada, M.: Collection of poetry (in Japanese). Reproduction of Ritsumeikan Publishing 1928 issued (1980)
Nitta, D.: Manners Series How to Make Chinese Poetry New Edition (in Japanese). Meiji Shoin (2003)
Okamoto, T.: Guidance on creating Chinese poetry at the secondary education level (in Japanese). Research Bulletin: Collection of Essays from Kobe University Secondary School 4, 9–14 (2020)
Onuki, M.: Lesson practice to provide “enrichment learning” in the unit of Chinese poetry in Japanese language course at senior high school: using a mock class for university students on creating rhyming poems in translation as a guide (in Japanese). J. Stud. Educ. Pract. 25, 12–22 (2022). https://doi.org/10.50841/kyoikujissen.25.0_12
Qiu, F., Nakamura, K., Komiya, S.: A proposal of a system to support the versification of a Chinese poem: constraints on versification and support for versification by utilizing a database of poetic dictionary (in Japanese). IEICE Tech. Rep. 111(211), 37–42 (2011)
Qiu, F., Nakamura, K., Komiya, S.: A proposal of system to support the versification of a Chinese poem : Constraints on versification and support for versification by utilizing a database of poetic diction (in Japanese). IEICE Tech. Rep. 112(300), 31–36 (2012)
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog (2019). https://openai.com/blog/better-language-models/
Wang, Z., et al.: Chinese poetry generation with planning based neural network. Proc of COLING 2016, 1051–1060 (2016)
Yi, X., Li, R., Sun, M.: Generating Chinese classical poems with RNN encoder-decoder. In: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, pp. 211–223 (2017)
Acknowledgment
This work was supported by JSPS KAKENHI, Grant Numbers JP20K12543 and JP23K11761.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Cong, Y., Takaku, M. (2023). Enhancing the Learning of Chinese Poem Creation Through an Auto-Generation and Evaluation System. In: Goh, D.H., Chen, SJ., Tuarob, S. (eds) Leveraging Generative Intelligence in Digital Libraries: Towards Human-Machine Collaboration. ICADL 2023. Lecture Notes in Computer Science, vol 14457. Springer, Singapore. https://doi.org/10.1007/978-981-99-8085-7_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-8085-7_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8084-0
Online ISBN: 978-981-99-8085-7
eBook Packages: Computer ScienceComputer Science (R0)