Elamur Research⌕
☰
home / papers / 2026 / New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants

New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants

Paper · 2026 · Xiaobin Shen, Zhongqing Wang, Shichen Li et al.

Summary

Classical Chinese botanical sources are hard to use today. They are written in terse classical language, cover a limited range of species, and lack modern taxonomy. The authors start from Guang Qun Fang Pu, a flower encyclopedia from the Qing dynasty that covers fewer than 500 plants, and expand it into a much larger multimodal resource.

Their pipeline has several parts:

  • Plant list. A list of common plants is derived from the Catalogue of Life China.
  • Text linking. Classical poems and prose are linked to plants in three stages: a dedicated model proposes candidate plants, an LLM picks one in a one-shot setting, and humans verify the result.
  • Enrichment. Each plant gets LLM-assisted modern classification, encyclopedic descriptions, and translations and literary appreciations of the texts.
  • Images. Ancient paintings and modern photographs are added.

On top of this resource, the authors propose a multimodal model that identifies which plant a classical text refers to. This is difficult because plant words in such texts often carry symbolic meaning rather than naming a concrete entity. Combining all information sources clearly outperforms text-only baselines. The work matters for digital humanities and for information extraction from classical Chinese.

Key points

  • Final dataset: 780 plant species, 44,298 related classical literary works, and 1,911 ancient and modern images.
  • Candidate list: the authors condensed the 47,474 species in Catalogue of Life China to 1,923 commonly occurring plants as candidates.
  • Baselines: a rule-based matcher (bge-large-zh-v1.5 similarity), Llama3-8B, MT5-base, Qwen2-7B, and IE models from other classical Chinese tasks. The proposed model beats all of them significantly (p < 0.05).
  • Ablation: using the literary text alone gives F1 0.5451. Adding translation, appreciation and encyclopedic knowledge together raises F1 to 0.7768. Using everything, including images, gives the best F1 of 0.7956.
  • Other multimodal models (LLaVA-v1.6-7b, Qwen2.5-VL-7b, MiniCPM-V-2_6, Gemma-3-4b-it) reach F1 between 0.65 and 0.79. The authors note as a limitation that the data are mostly poetry, which may restrict generalization to other genres.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Soochow UniversitySuzhou · China69 works · 4,815 citations🎓Hong Kong Polytechnic UniversityHong Kong · China106 works · 5,190 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 works

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 811 works

Cite

Cite as Xiaobin Shen, Zhongqing Wang, Shichen Li, Chu-Ren Huang and Guodong Zhou. 2026. New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.73

@inproceedings{shen2026new,
  title = {{New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants}},
  author = {Xiaobin Shen, Zhongqing Wang, Shichen Li, Chu-Ren Huang and Guodong Zhou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.73},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.73}
}

References

64 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. Qwen2.5-vl technical report. Preprint, arXiv:2502.13…
  2. Xiaoyi Bao, Zhongqing Wang, Jinghang Gu, and Chu-Ren Huang. 2025. Revisiting classical Chinese event extraction with ancient literature information. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8440–8451, Vienna, Austria. A… find
  3. Baptiste Blouin, Cécile Armand, and Christian Henriot. 2024. A dataset for named entity recognition and entity linking in chinese historical newspapers. In LREC-COLING 2024. find
  4. Chang Bolin. 2021. The construction and application for digital humanities knowledge base of ancient books based on word and entity annotation: A case study on \<i\>zhou qin han annals ofzizhitongjian\</i\>. Library and Information Service, 65(22):134. find
  5. Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, and Lianwen Jin. 2024a. Tonggu: Mastering classical chinese understanding with knowledge-grounded large language models. arXiv preprint arXiv:2407.03937. find
  6. Jiahuan Cao, Yongxin Shi, Dezhi Peng, Yang Liu, and Lianwen Jin. 2024b. CΘ {3} bench: A comprehensive classical chinese understanding benchmark for large language models. arXiv preprint arXiv:2405.17732. — [arXiv:2405.17732](https://arxiv.org/abs/2405.17732) find
  7. Yu Chang, Peng Zhu, Chaoping Wang, and Chaofan Wang. 2022. Automatic word segmentation and part-of-speech tagging of ancient chinese based on bert model. In Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, pages 141–145. find
  8. Li Chen. 2022. Digitalization of ancient books and construction of classical knowledge repository from the perspective of digital humanities. Journal of library science in China, 48(02):36–46. find
  9. Wei Congcong, Feng Zhenbing, Huang Shutan, Li Wei, and Shao Yanqiu. 2023. Ched: A cross-historical dataset with a logical event schema for classical chinese event detection. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 875–888. find
  10. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. Preprint,…
  11. Luan Feng, Du Yazhou, Luo Ying, Liu Zhipeng, and Batima Sairekjiang. 2024. Research on traditional chinese medicine named entity recognition based on shang han lun. Information and Computer (Theoretical Edition), 36(20):19–22. find
  12. Ping Feng, Jingyu Kang, Biao Huang, Shulai Wang, and Jialun Li. 2022. A method of named entity recognition in classical chinese based on bert-ancient-chinese. In 2022 4th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), pages 137–141. find
  13. Alex Henry, Prudhvi Raj Dachapally, Shubham Pawar, and Yuxuan Chen. 2020. Query-key normalization for transformers. Preprint, arXiv:2010.04245. find
  14. Baha Ihnaini, Weiyi Sun, Yingchao Cai, Zhijun Xu, and Rashid Sangi. 2024. Sentiment analysis of song dynasty classical poetry using fine-tuned large language models: A study with llms. In 2024 7th International Conference on Artificial Intelligence and Big Data (ICAIBD), pages 590–597. find
  15. Longjie Jiang, Qinyu C Chang, Huyin H Xie, and Zhuying Z Xia. 2022. Construction of segmentation and part of speech annotation model in ancient chinese. In Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, pages 155–158. find
  16. Zongyuan Jiang, Jiapeng Wang, Jiahuan Cao, Xue Gao, and Lianwen Jin. 2023. Towards better translations from classical to modern chinese: A new dataset and a new method. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 387–399. Springer. find
  17. Wenjun Kang, Jiali Zuo, Yiyu Hu, and Mingwen Wang. 2024. Historical event detection in classical chinese based on incremental pre-training and external knowledge. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 191–200, Taiyuan, Chin… find
  18. Mengfei Li and Xiaohuan Zheng. 2023. Identification of ancient chinese medical prescriptions and case data analysis under artificial intelligence gpt algorithm: a case study of song dynasty medical literature. Ieee Access, 11:131453–131464. find
  19. Yuqing Li, Yuxin Zhang, Bin Wu, Ji-Rong Wen, Ruihua Song, and Ting Bai. 2022. A multi-modal knowledge graph for classical chinese poetry. In Findings of the association for computational linguistics: EMNLP 2022, pages 2318–2326. find
  20. Ke Liang, Chu-Ren Huang, and Xin-Lan Jiang. 2024. From text to historical ecological knowledge: The construction and application of the Shan jing knowledge base. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 202… find
  21. Chao-Lin Liu, Wei-Ting Chang, Chang-Ting Chu, and Ti-Yong Zheng. 2024a. Machine learning and data analysis for word segmentation of classical chinese poems: illustrations with tang and song examples. Digital Scholarship in the Humanities, 39(1):228– 241. find
  22. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023a. Visual instruction tuning. Preprint, arXiv:2304.08485.
  23. Liu Liu, Chufei Liu, Wenqi Li, Dongbo Wang, and Shuiqing Huang. 2024b. Perspective of digital humanities on person names in chinese pre-qin classic. ACM Journal on Computing and Cultural Heritage, 17(2):1–19. find
  24. Yunxiang Liu and Mengtian Liu. 2024. Research on named entity recognition of traditional chinese medicine text based on roberta-bilstm-crf. In 2024 9th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), volume 9, pages 130–135. IEEE. find
  25. Lin Qi, Yuwei Wang, Jindong Chen, Mengjie Liao, and Jian Zhang. 2021. Culture under complex perspective: a classification for traditional chinese cultural elements based on nlp and complex networks. Complexity, 2021(1):6693753. find
  26. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. Preprint, arXiv:2103.00020.
  27. MS Rajeevan, Chakala Mallikarjuna, Anoop VS, and 1 others. 2020. Nlp-driven knowledge extraction and thematic classification of translated ancient indian medical texts. Rajeevan, MS, Mini devi, B., Anoop, VS, & Mallikarjuna, C.(2025). NLP-driven Knowledge Extraction and Thematic Classification of Tr… find
  28. Shijing Si, Siqing Zhou, and Yugui Zhang. 2024. Exploring the capabilities of chatgpt in ancient chinese translation and person name recognition. Corpus-based Studies across Humanities, 2(2):221–234. find
  29. Bingyan Song, Zhenshan Bao, YueZhang Wang, Wenbo Zhang, and Chao Sun. 2020. Incorporating lexicon for named entity recognition of traditional chinese medicine books. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 481–489. Springer. find
  30. Xuemei Tang, Zekun Deng, Qi Su, Hao Yang, and Jun Wang. 2024a. Chisiec: an information extraction corpus for ancient chinese history. arXiv preprint arXiv:2403.15088. find
  31. Xuemei Tang, Zekun Deng, Qi Su, Hao Yang, and Jun Wang. 2024b. CHisIEC: An information extraction corpus for Ancient Chinese history. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3192–3202, Torino,… find
  32. Xuemei Tang, Zekun Deng, Qi Su, Hao Yang, and Jun Wang. 2024c. Chisiec: An information extraction corpus for ancient chinese history. Preprint, arXiv:2403.15088. find
  33. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. Preprint, arXiv:1711.05101. find
  34. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… find
  35. Hengnian Qi, Hao Yang, Zhaojiang Wang, Jiabin Ye, Qiuyi Xin, Chu Zhang, and Qing Lang. 2025. An-cientglyphnet: an advanced deep learning framework for detecting ancient chinese characters in complex scene. Artificial Intelligence Review, 58(3):88. find
  36. Huishuang Tian, Kexin Yang, Dayiheng Liu, and Jiancheng Lv. 2021. Anchibert: A pre-trained model for ancient chinese language understanding and generation. In 2021 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE. find
  37. Zhou Liu, Hongsu Wang, and Peter K Bol. 2023b. Automatic biographical information extraction from local gazetteers with bi-lstm-crf model and bert. International Journal of Digital Humanities, 4(1):195–212. find
  38. Yanzhi Tian and Yuhang Guo. 2022. Ancient Chinese word segmentation and part-of-speech tagging using data augmentation. In Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, pages 146–149, Marseille, France. European Language Resources Association. find
  39. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. Preprint…
  40. Nick J Turland, John Harry Wiersema, Fred R Barrie, Werner Greuter, David L Hawksworth, Patrick Stephen Herendeen, Sandra Knapp, Wolf-Henning Kusber, De-Zhu Li, Karol Marhold, and 1 others. 2018. International Code of Nomenclature for algae, fungi, and plants (Shenzhen Code) adopted by the Nineteent… find
  41. Dongbo Wang, Chang Liu, Zhixiao Zhao, Si Shen, Liu Liu, Bin Li, Haotian Hu, Mengcheng Wu, Litao Lin, Xue Zhao, and 1 others. 2023. Gujibert and gujigpt: Construction of intelligent information processing foundation language models for ancient texts. arXiv preprint arXiv:2307.05354. — [arXiv:2307.05354](https://arxiv.org/abs/2307.05354) find
  42. Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, Zhaokai Wang, Zhe Chen, Hongjie Zhang, Ganlin Yang, Haomin Wang, Qi Wei, Jinhui Yin, Wenhao Li, Erfei Cui, and 56 others. 2025. Internvl3.5: Advancing open-source multimodal…
  43. Rachel Wicks and Matt Post. 2021. A unified approach to sentence segmentation of punctuated text in many languages. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Pa…
  44. Janyce Wiebe, Theresa Wilson, and Claire Cardie. 2005. Annotating expressions of opinions and emotions in language. Language resources and evaluation, 39(2):165–210. find
  45. MC Wu, LT Lin, Y Qi, SQ Huang, DB Wang, and L Liu. 2023a. Plant knowledge mining and organization construction in pre-qin classics from the perspective of digital humanities. Library and Information Service, 67(12):103–113. find
  46. Ziwei Wu, Yuxuan Liu, Qingao Huo, and Wendong Zhang. 2023b. Named entity recognition of tcm classics based on sikubert and multi-feature embedding. In 2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE), pages 73–77. IEEE. find
  47. Shate Xiang, Huanxiang Lin, Fen Cai, and Zhehan Jiang. 2025. Integrating knowledge graphs with ancient chinese medicine classics: challenges and future prospects of multi-agent system convergence. Chinese Medicine, 20(1):168. find
  48. Han Xu, Wang Hongsu, Zhang Sanqian, Fu Qunchao, and Liu Jun. 2019. Sentence segmentation for classical chinese based on lstm with radical embedding. The Journal of China Universities of Posts and Telecommunications, 26(02):1–8. find
  49. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Ling…
  50. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 43 others. 2024. Qwen2 technical report. Preprint, arXiv:240… find
  51. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, Qianyu Chen, Huarong Zhou, Zhensheng Zou, Haoye Zhang, Shengding Hu, Zhi Zheng, Jie Zhou, Jie Cai, Xu Han, and 4 others. 2024. Minicpmv: A gpt-4v level mllm on your phone. Preprint, arX…
  52. Xuehan Yu, Lin He, and Jian Xu. 2021. Extracting events from ancient books based on roberta-crf. Data Analysis and Knowledge Discovery, 5(7):26–35. find
  53. Charles Woodrum, Brian Joseph, Antoine Haaker, and Christopher Brown. 2025. Named entity recognition on ancient languages using large language models: An exploratory study. In International Conference on Human-Computer Interaction, pages 430–439. Springer. find
  54. Du Yue, Wang Dongbo, Jiang Chuan, Xu Runhua, Li Bin, Xu Chao, and Xu Chenfei. 2021. Construction and application of an automatic entity recognition model for classics based on deep learning in digital humanities. Library and Information Service, 65(3):100–108. find
  55. Lingjing Wu, Chuang Zhang, Mengqiu Xu, and Ming Wu. 2021. Ancient chinese recognition method based on attention mechanism. In 2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC), pages 309–313. IEEE. find
  56. Dezheng Zhang, Chao Xia, Cong Xu, Qi Jia, Shibing Yang, Xiong Luo, and Yonghong Xie. 2020. Improving distantly-supervised named entity recognition for traditional chinese medicine text via a novel back-labeling approach. IEEE Access, 8:145413–145421. find
  57. Yixuan Zhang and Haonan Li. 2023a. Can large language model comprehend Ancient Chinese? a preliminary test on ACLUE. In Proceedings of the Ancient Language Processing Workshop, pages 80–87, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria. find
  58. Yixuan Zhang and Haonan Li. 2023b. Can large language model comprehend ancient chinese? a preliminary test on aclue. arXiv preprint arXiv:2310.09550. find
  59. Zhen Zhang, Yuhua Zhao, Hang Gao, and Mengting Hu. 2024. Linkner: Linking local named entity recognition models to large language models using uncertainty. Preprint, arXiv:2402.10573. — [arXiv:2402.10573](https://arxiv.org/abs/2402.10573) find
  60. YueYan Zhao and WenJie Zhou. 2025. Unlocking ancient wisdom with modern tools: A new approach to the revitalization of ancient texts based on generative artificial intelligence. The Journal of Academic Librarianship, 51(3):103055. find
  61. Xiang Zheng, Mingjie Li, and Jingpeng Deng. 2025. Simplifying knowledge acquisition of ancient chinese agricultural books: a method for structure function recognition of bibliographic summaries. Aslib Journal of Information Management, pages 1–21. find
  62. Xiang Zheng, Mingjie Li, Ze Wan, and Yan Zhang. 2024. Knowledge mining and graph visualization of ancient chinese scientific and technological documents bibliographic summaries based on digital humanities. Library Hi Tech, 42(6):1693–1721. find
  63. Bo Zhou, Qianglong Chen, Tianyu Wang, Xiaomi Zhong, and Yin Zhang. 2023. Wyweb: A nlp evaluation benchmark for classical chinese. arXiv preprint arXiv:2305.14150. find
  64. Ying Zhou, Yang Zhou, and Yao Liu. 2024. Research on ontology construction based on the knowledge system of ‘compendium of materia medica’. In 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), pages 642–645. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/shen-2026-new-compendium-myriad-plants-new/