---
title: "From Shijing to English and German: Resources and Evaluation"
description: "The authors focus on the Feng section and build two resources. 68 references. Among them: 0."
authors: ["Ying Jiao", "Meng Sun"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.542/"
doi: "10.18653/v1/2026.findings-acl.542"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/jiao-2026-shijing-english-german-resources-evaluation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/jiao-2026-shijing-english-german-resources-evaluation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/) / From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry

# From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry

**Authors:** Ying Jiao and Meng Sun · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.542/) · [PDF](https://aclanthology.org/2026.findings-acl.542.pdf) · [DOI 10.18653/v1/2026.findings-acl.542](https://doi.org/10.18653/v1/2026.findings-acl.542) · [OpenAlex](https://openalex.org/W7166866990)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper asks how well current LLMs translate the *Shijing* (Book of Songs), the oldest Chinese poetry collection. The text is hard because of archaic vocabulary, phonetic loans, culture-bound terms and formulaic repetition. Two gaps block automatic study: there are few multilingual reference resources, and standard metrics such as BLEU and COMET miss poetic form and literary quality. The authors focus on the Feng section and build two resources. The first is a Chinese–English–German corpus aligned line by line, with several human translations per poem. The second is an expert-built lexical knowledge base of difficult archaic expressions, each given English and German renderings. On top of these they design a hybrid evaluation that combines three parts: knowledge-driven checks of semantic accuracy, rule-based scoring of form and rhyme, and LLM-as-judge scoring used only for artistic conception. The framework agrees with human judgments much better than traditional metrics and ranks systems stably. Across seven LLMs, Gemini-2.5-Pro and DeepSeek-3.1 lead, but no model reaches consistently high quality. German output is clearly weaker than English.

## Key points
- **Corpus:** all 160 Feng poems, aligned line by line.
  - Four English translations: Legge 1871, Jennings 1891, Waley 1937, Xu 1993.
  - Two German translations: von Strauß 1880, Simon 2015.
  - Poems average 16.3 lines.
  - Vocabulary size: 1676 unique Chinese characters, against 10,882 English and 7826 German word types.
- **Lexical KB:** 1195 entries, about 7.5 per poem, compiled by a Shijing translation specialist from classical commentaries.
  - Each entry is tagged with one of four types: tongjia (phonetic loan), term for object, culture-specific item, or confusable character.
- **Evaluation setup:**
  - The metric was validated against human ratings on a 60-poem subset.
  - Overall scores in [0, 1] are also mapped to a 1–5 scale, purely for readability.
  - A CoDeC check found no evidence that models had memorized the reference translations.
- **Model results:**
  - Gemini-2.5-Pro is best on accuracy, literariness and overall quality in both languages.
  - DeepSeek-3.1 is the strongest open-source model.
  - LLaMA-3.1-8B is weak on both meaning and style.
- **Language gap and release:** Chinese→German trails Chinese→English for every model. Because of copyright, the authors release code, the KB and a corpus reconstruction protocol rather than the full corpus.

## Interesting ideas
- An expert list of "trap" expressions, each with accepted target renderings, allows a targeted and interpretable adequacy check that a global similarity score cannot give.
- Measurable properties such as rhyme and form are scored by deterministic rules, and the LLM judge handles only the dimension rules cannot capture. This keeps most of the score explainable.
- Each source line has several independent human references, so legitimate ambiguity and stylistic variation are not punished as errors.
- A typed taxonomy of lexical difficulty (loan readings, confusable forms, culture-bound terms) turns raw errors into diagnosable categories.
- A new metric is validated in three ways: correlation with human ratings, stability of system rankings across languages, and a contamination check on the references.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (back): when testing text → graph → text and meta-world translation, keep a curated list of hard items (idioms, archaic or polysemous words) and check that each one survives the round trip, reporting exactly which ones fail.
- **I2** (learn): use LLM teacher tiers only for residual, rule-resistant judgments, while structural checks stay rule-based and auditable.
- **I3** (learn): keep multiple acceptable analyses as witnesses instead of a single gold, so evaluation does not penalize valid alternatives in ambiguous constructions.
- **I4** (tokens): tag archaic or confusable English forms (e.g. in fables and tales) by error type, so lemma and tagger mistakes can be grouped and repaired systematically.
- **I5** (learn): validate any new automatic score the same way, adding ranking-stability tests and leakage checks as negative controls.

*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

- [KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/) — University, Leuven, Belgium · 42 works · 5,839 citations
- [Shanghai International Studies University](https://md.research.elamur.ai/free/en/universities/shanghai-international-studies-university/) — University, Shanghai, China · 3 works · 29 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works

## Cite

Cite as: Ying Jiao and Meng Sun. 2026. From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{jiao2026shijing,
  title = {{From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry}},
  author = {Ying Jiao and Meng Sun},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.542},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.542}
}
```

- [← previous From Script to Semantics: Prompting Strategies for African NLI](https://md.research.elamur.ai/free/en/papers/tiwari-2026-script-semantics-prompting-strategies-african/)
- [next → From Short Video to Clickable Search: RLVR-Enabled Listwise Query Suggestion with Retrieval-Augmented Context](https://md.research.elamur.ai/free/en/papers/tian-2026-short-video-clickable-search-rlvr/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/)

## References

68 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Baidu Inc. 2025. Ernie 4.5 technical report. Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=Baidu+Inc%2E+2025%2E+Ernie+4%2E5+technical+report%2E+Accessed%3A+2026%2D01%2D02%2E)
2. Satanjeev Banerjee and Alon Lavie. 2005. [Meteor: An automatic metric for mt evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72.
3. William H Baxter. 1992. A Handbook of Old Chinese Phonology. Mouton de Gruyter, Berlin. [↗](https://doi.org/10.1515/9783110857085)
4. Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, and others. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International conference on machine learning, pages 2397–2430. PMLR. [find](https://scholar.google.com/scholar?q=Stella+Biderman%2C+Hailey+Schoelkopf%2C+Quentin+Gregory+Anthony%2C+Herbie+Bradley%2C+Kyle+O%E2%80%99Brien%2C+Eric+Hallahan%2C+Mohammad+Aflah+Khan%2C+Shivanshu+Purohit%2C+USVSN+Sai+Prashanth%2C+Edward+Raff%2C+and+others%2E+2023%2E+Py)
5. Zong-qi Cai. 2008. How to read Chinese poetry: A guided anthology. Columbia University Press, New York. [find](https://scholar.google.com/scholar?q=Zong%2Dqi+Cai%2E+2008%2E+How+to+read+Chinese+poetry%3A+A+guided+anthology%2E+Columbia+University+Press%2C+New+York%2E)
6. Carnegie Mellon University. 2014. The CMU pronouncing dictionary. [find](https://scholar.google.com/scholar?q=Carnegie+Mellon+University%2E+2014%2E+The+CMU+pronouncing+dictionary%2E)
7. Tuhin Chakrabarty, Arkadiy Saakyan, and Smaranda Muresan. 2021. Don’t go far off: An empirical study on neural poetry translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7253–7265. [↗](https://doi.org/10.48550/arxiv.2109.02972)
8. Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao, and Min Zhang. 2025. [Benchmarking llms for translating classical chinese poetry: Evaluating adequacy, fluency, and elegance](https://md.research.elamur.ai/free/en/papers/chen-2025-benchmarking-llms-translating-classical-chinese/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 33019–33036.
9. Huimin Chen, Xiaoyuan Yi, Maosong Sun, Wenhao Li, Cheng Yang, and Zhipeng Guo. 2019. Sentiment-controllable chinese poetry generation. In IJCAI, pages 4925–4931. [find](https://scholar.google.com/scholar?q=Huimin+Chen%2C+Xiaoyuan+Yi%2C+Maosong+Sun%2C+Wenhao+Li%2C+Cheng+Yang%2C+and+Zhipeng+Guo%2E+2019%2E+Sentiment%2Dcontrollable+chinese+poetry+generation%2E+In+IJCAI%2C+pages+4925%E2%80%934931%2E)
10. Junying Cheng and Jianyuan Jiang. 2017. Commentary on Shijing (诗经注析). Zhonghua Book Company, Beijing. In Chinese; ISBN: 9787101126914. [find](https://scholar.google.com/scholar?q=Junying+Cheng+and+Jianyuan+Jiang%2E+2017%2E+Commentary+on+Shijing+%28%E8%AF%97%E7%BB%8F%E6%B3%A8%E6%9E%90%29%2E+Zhonghua+Book+Company%2C+Beijing%2E+In+Chinese%3B+ISBN%3A+9787101126914%2E)
11. Cheng-Han Chiang and Hung-Yi Lee. 2023. Can large language models be an alternative to human evaluations? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15607–15631. [find](https://scholar.google.com/scholar?q=Cheng%2DHan+Chiang+and+Hung%2DYi+Lee%2E+2023%2E+Can+large+language+models+be+an+alternative+to+human+evaluations%3F+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Vo)
12. Domenic V Cicchetti. 1994. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychological Assessment, 6(4):284–290. [↗](https://doi.org/10.1037//1040-3590.6.4.284)
13. DeepSeek. 2025. Deepseek v3.1 release. Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=DeepSeek%2E+2025%2E+Deepseek+v3%2E1+release%2E+Accessed%3A+2026%2D01%2D02%2E)
14. Reece Dunn, Alexander Epaneshnikov, and others. 2024. eSpeak-NG: Compact open source speech synthesizer. Open source text-to-speech software, GPL-3.0 licensed. [find](https://scholar.google.com/scholar?q=Reece+Dunn%2C+Alexander+Epaneshnikov%2C+and+others%2E+2024%2E+eSpeak%2DNG%3A+Compact+open+source+speech+synthesizer%2E+Open+source+text%2Dto%2Dspeech+software%2C+GPL%2D3%2E0+licensed%2E)
15. Heng Gao. 2009. Modern Annotations on the Book of Songs (诗 经 今 注). Shanghai Classics Publishing House, Shanghai. In Chinese; ISBN: 9787532553136;. [find](https://scholar.google.com/scholar?q=Heng+Gao%2E+2009%2E+Modern+Annotations+on+the+Book+of+Songs+%28%E8%AF%97+%E7%BB%8F+%E4%BB%8A+%E6%B3%A8%29%2E+Shanghai+Classics+Publishing+House%2C+Shanghai%2E+In+Chinese%3B+ISBN%3A+9787532553136%3B%2E)
16. Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, and others. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027. [↗](https://arxiv.org/abs/2101.00027)
17. Dmitriy Genzel, Jakob Uszkoreit, and Franz Josef Och. 2010. “poetic” statistical machine translation: rhyme and meter. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 158–166. [find](https://scholar.google.com/scholar?q=Dmitriy+Genzel%2C+Jakob+Uszkoreit%2C+and+Franz+Josef+Och%2E+2010%2E+%E2%80%9Cpoetic%E2%80%9D+statistical+machine+translation%3A+rhyme+and+meter%2E+In+Proceedings+of+the+2010+Conference+on+Empirical+Methods+in+Natural+Language+Pr)
18. Google DeepMind. 2025. Gemini 2.5: Our newest gemini model with thinking. Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2025%2E+Gemini+2%2E5%3A+Our+newest+gemini+model+with+thinking%2E+Accessed%3A+2026%2D01%2D02%2E)
19. Marcel Granet. 2015. Festivals and songs of ancient China. Routledge, New York. [↗](https://doi.org/10.4324/9781315646787)
20. Roland Greene, Stephen Cushman, Clare Cavanagh, Jahan Ramazani, and Paul Rouzer. 2012. The Princeton Encyclopedia of Poetry and Poetics. Princeton University Press, Princeton. [↗](https://doi.org/10.1515/9781400841424)
21. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, Adriane Boyd, and others. 2020. spacy: Industrial-strength natural language processing in python. iFLYTEK. 2025. iflytek spark large model series (including 4.0). Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal%2C+Ines+Montani%2C+Sofie+Van+Lan%2Ddeghem%2C+Adriane+Boyd%2C+and+others%2E+2020%2E+spacy%3A+Industrial%2Dstrength+natural+language+processing+in+python%2E+iFLYTEK%2E+2025%2E+iflytek+spark+large+model+series+)
22. William Jennings. 1891. The Shi King. The old "Poetry Classic" of the Chinese. George Routledge and Sons, London. [find](https://scholar.google.com/scholar?q=William+Jennings%2E+1891%2E+The+Shi+King%2E+The+old+%22Poetry+Classic%22+of+the+Chinese%2E+George+Routledge+and+Sons%2C+London%2E)
23. Bernhard Karlgren. 1950. The Book of Odes. Museum of Far Eastern Antiquities, Stockholm. [find](https://scholar.google.com/scholar?q=Bernhard+Karlgren%2E+1950%2E+The+Book+of+Odes%2E+Museum+of+Far+Eastern+Antiquities%2C+Stockholm%2E)
24. Maurice G Kendall. 1938. A new measure of rank correlation. Biometrika, 30(1-2):81–93. [↗](https://doi.org/10.1093/biomet/30.1-2.81)
25. Ha Poong Kim. 2016. Joy and Sorrow Songs of Ancient China: A New Translation of Shi Jing Guo Feng. Liverpool University Press, Liverpool. [find](https://scholar.google.com/scholar?q=Ha+Poong+Kim%2E+2016%2E+Joy+and+Sorrow+Songs+of+Ancient+China%3A+A+New+Translation+of+Shi+Jing+Guo+Feng%2E+Liverpool+University+Press%2C+Liverpool%2E)
26. Klaus Krippendorff. 2019. Content analysis: An introduction to its methodology. Sage publications, Thousand Oaks. [↗](https://doi.org/10.4135/9781071878781)
27. James Legge. 1871. The Chinese Classics. Vol. IV. The She-King, or the Book of Poetry. Lane, Crawford Co, Hong Kong. [find](https://scholar.google.com/scholar?q=James+Legge%2E+1871%2E+The+Chinese+Classics%2E+Vol%2E+IV%2E+The+She%2DKing%2C+or+the+Book+of+Poetry%2E+Lane%2C+Crawford+Co%2C+Hong+Kong%2E)
28. Wenhao Li, Fanchao Qi, Maosong Sun, Xiaoyuan Yi, and Jiarui Zhang. 2021. Ccpm: A chinese classical poetry matching dataset. arXiv preprint arXiv:2106.01979. [↗](https://arxiv.org/abs/2106.01979)
29. Rensis Likert. 1932. A technique for the measurement of attitudes. Archives of Psychology, New York. [find](https://scholar.google.com/scholar?q=Rensis+Likert%2E+1932%2E+A+technique+for+the+measurement+of+attitudes%2E+Archives+of+Psychology%2C+New+York%2E)
30. Chin-Yew Lin. 2004. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81.
31. Yutong Liu, Bin Wu, and Ting Bai. 2020. The construction and analysis of classical chinese poetry knowledge graph. Journal of Computer Research and Development, 57(6):1252–1268. [↗](https://doi.org/10.7544/issn1000-1239.2020.20190641)
32. Peter Robinson. 2010. Poetry & Translation: The Art of the Impossible. Liverpool University Press, Liverpool. [find](https://scholar.google.com/scholar?q=Peter+Robinson%2E+2010%2E+Poetry+%26+Translation%3A+The+Art+of+the+Impossible%2E+Liverpool+University+Press%2C+Liverpool%2E)
33. Edward Loper and Steven Bird. 2002. Nltk: The natural language toolkit. In Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, pages 63–70. [↗](https://doi.org/10.48550/arxiv.cs/0205028)
34. Vinay Samuel, Yue Zhou, and Henry Peng Zou. 2025. [Towards data contamination detection for modern large language models: Limitations, inconsistencies, and oracle challenges](https://md.research.elamur.ai/free/en/papers/samuel-2025-data-contamination-detection-modern-large/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 5058–5070. [↗](https://doi.org/10.48550/arxiv.2409.09927)
35. Hualiang Lv. 2015. Shijing: An Analysis of Objects - Feng (诗 经 名 物 注 析 国 风 篇). Huangshan Book Company, Hefei. In Chinese; ISBN: 9787546150451;. [find](https://scholar.google.com/scholar?q=Hualiang+Lv%2E+2015%2E+Shijing%3A+An+Analysis+of+Objects+%2D+Feng+%28%E8%AF%97+%E7%BB%8F+%E5%90%8D+%E7%89%A9+%E6%B3%A8+%E6%9E%90+%E5%9B%BD+%E9%A3%8E+%E7%AF%87%29%2E+Huangshan+Book+Company%2C+Hefei%2E+In+Chinese%3B+ISBN%3A+9787546150451%3B%2E)
36. Haun Saussy. 1997. Repetition, rhyme, and exchange in the book of odes. Harvard Journal of Asiatic Studies, 57(2):519–542. [↗](https://doi.org/10.2307/2719486)
37. William McNaughton. 1963. The composite image: Shy jing poetics. Journal of the American Oriental Society, 83(1):92–106. [↗](https://doi.org/10.2307/597768)
38. Piotr Sawicki, Marek Grześ, Dan Brown, and Fabrício Góes. 2025. Can large language models outperform non-experts in poetry evaluation? a comparative study using the consensual assessment technique. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, page 31901–31918. [find](https://scholar.google.com/scholar?q=Piotr+Sawicki%2C+Marek+Grzes%CC%81%2C+Dan+Brown%2C+and+Fabr%C3%ADcio+G%C3%B3es%2E+2025%2E+Can+large+language+models+outperform+non%2Dexperts+in+poetry+evaluation%3F+a+comparative+study+using+the+consensual+assessment+technique%2E+I)
39. Meta AI. 2024. Introducing llama 3.1: Our most capable models to date. Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=Meta+AI%2E+2024%2E+Introducing+llama+3%2E1%3A+Our+most+capable+models+to+date%2E+Accessed%3A+2026%2D01%2D02%2E)
40. OpenAI. 2025. Gpt-5 is here. Accessed: 2026-01-02. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt%2D5+is+here%2E+Accessed%3A+2026%2D01%2D02%2E)
41. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318. [↗](https://doi.org/10.3115/1073083.1073135)
42. Karl Pearson. 1895. Vii. note on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London, 58(347-352):240–242. [↗](https://doi.org/10.1098/rspl.1895.0041)
43. Maja Popović. 2017. [chrf++: words helping character n-grams](https://md.research.elamur.ai/free/en/papers/popovic-2017-chrf-words-helping-character-n/). In Proceedings of the second conference on machine translation, pages 612–618.
44. Matt Post. 2018. [A call for clarity in reporting BLEU scores](https://md.research.elamur.ai/free/en/papers/post-2018-call-clarity-reporting-bleu-scores/). In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Belgium, Brussels. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/w18-6319)
45. Amy Pu, Hyung Won Chung, Ankur Parikh, Sebastian Gehrmann, and Thibault Sellam. 2021. [Learning compact metrics for mt](https://md.research.elamur.ai/free/en/papers/pu-2021-learning-compact-metrics-mt/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 751–762.
46. Burton Raffel. 1988. The art of translating poetry. Pennsylvania State University Press, University Park, London. [↗](https://doi.org/10.1515/9780271072807)
47. Ricardo Rei, José GC De Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and André FT Martins. 2022. [Comet-22: Unbabel-ist 2022 submission for the metrics shared task](https://md.research.elamur.ai/free/en/papers/rei-2022-comet-22-unbabel-ist-2022/). In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 578–585.
48. Ricardo Rei, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. [Comet: A neural framework for mt evaluation](https://md.research.elamur.ai/free/en/papers/rei-2020-comet-neural-framework-mt-evaluation/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2685–2702.
49. Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020. [Bleurt: Learning robust metrics for text generation](https://md.research.elamur.ai/free/en/papers/sellam-2020-bleurt-learning-robust-metrics-text/). In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 7881– 7892.
50. Edward L Shaughnessy. 1992. Marriage, divorce, and revolution: Reading between the lines of the book of changes. The Journal of Asian Studies, 51(3):587– 599. [find](https://scholar.google.com/scholar?q=Edward+L+Shaughnessy%2E+1992%2E+Marriage%2C+divorce%2C+and+revolution%3A+Reading+between+the+lines+of+the+book+of+changes%2E+The+Journal+of+Asian+Studies%2C+51%283%29%3A587%E2%80%93+599%2E)
51. Patrick E Shrout and Joseph L Fleiss. 1979. Intraclass correlations: uses in assessing rater reliability. Psychological bulletin, 86(2):420–428. [↗](https://doi.org/10.1037//0033-2909.86.2.420)
52. Rainald Simon. 2015. Shijing: Das altchinesische Buch der Lieder. Reclam, Ditzingen. In German; ISBN: 9783150108659;. [find](https://scholar.google.com/scholar?q=Rainald+Simon%2E+2015%2E+Shijing%3A+Das+altchinesische+Buch+der+Lieder%2E+Reclam%2C+Ditzingen%2E+In+German%3B+ISBN%3A+9783150108659%3B%2E)
53. Jonathan Smith. 2015. Sound symbolism in the reduplicative vocabulary of the shijing. Journal of Chinese Literature and Culture, 2(2):258–285. [↗](https://doi.org/10.1215/23290048-3324236)
54. Wai Lei Song, Haoyun Xu, Derek F Wong, Runzhe Zhan, Lidia S Chao, and Shanshan Wang. 2023. Towards zero-shot multilingual poetry translation. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 324–335. [find](https://scholar.google.com/scholar?q=Wai+Lei+Song%2C+Haoyun+Xu%2C+Derek+F+Wong%2C+Runzhe+Zhan%2C+Lidia+S+Chao%2C+and+Shanshan+Wang%2E+2023%2E+Towards+zero%2Dshot+multilingual+poetry+translation%2E+In+Proceedings+of+Machine+Translation+Summit+XIX%2C+Vol%2E+1%3A+)
55. Yunhong Song. 2025. The research trends and prospect of translation studies of the book of songs — based on citespace literature visualization analysis (《诗 经》翻译研究动态与展望-基于CiteSpace的文献 可视化分析). Modern Linguistics, 13:284–292. [find](https://scholar.google.com/scholar?q=Yunhong+Song%2E+2025%2E+The+research+trends+and+prospect+of+translation+studies+of+the+book+of+songs+%E2%80%94+based+on+citespace+literature+visualization+analysis+%28%E3%80%8A%E8%AF%97+%E7%BB%8F%E3%80%8B%E7%BF%BB%E8%AF%91%E7%A0%94%E7%A9%B6%E5%8A%A8%E6%80%81%E4%B8%8E%E5%B1%95%E6%9C%9B%2D%E5%9F%BA%E4%BA%8ECiteSpace%E7%9A%84%E6%96%87%E7%8C%AE+%E5%8F%AF%E8%A7%86%E5%8C%96%E5%88%86%E6%9E%90%29%2E+Modern+Li)
56. Charles Spearman. 1961. The proof and measurement of association between two things. In J. J. Jenkins and D. G. Paterson, editors, Studies in Individual Differences: The Search for Intelligence, pages 45– 58. Appleton-Century-Crofts, New York. Reprinted from The American Journal of Psychology, 15, 72– 101 (1904). [↗](https://doi.org/10.1037/11491-005)
57. Katherine Thai, Marzena Karpinska, Kalpesh Krishna, Bill Ray, Moira Inghilleri, John Wieting, and Mohit Iyyer. 2022. Exploring document-level literary machine translation with parallel paragraphs from world literature. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9882–9902. [find](https://scholar.google.com/scholar?q=Katherine+Thai%2C+Marzena+Karpinska%2C+Kalpesh+Krishna%2C+Bill+Ray%2C+Moira+Inghilleri%2C+John+Wieting%2C+and+Mohit+Iyyer%2E+2022%2E+Exploring+document%2Dlevel+literary+machine+translation+with+parallel+paragraphs+from)
58. Ran Zhang, Wei Zhao, and Steffen Eger. 2025. How good are llms for literary translation, really? literary translation evaluation with humans and llms. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 10961–10988. [↗](https://doi.org/10.48550/arxiv.2410.18697)
59. Victor von Strauß. 1880. Schı̄-kı̄ng: Das kanon-ische Liederbuch der Chinesen. Carl Winter’s Universitätsbuchhandlung, Heidelberg. In German; [https://books.google.de/books/about/Schi_](https://books.google.de/books/about/Schi_) king.html?id=NhF4em_jMZ8C&redir_esc=y. [↗](https://books.google.de/books/about/Schi_)
60. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations. https://arxiv.org/abs/1904.09675. [↗](https://arxiv.org/abs/1904.09675)
61. Hans-Günter Wagner. 2007. Hell ein Vogelruf ertönt: Altchinesische Volkslyrik aus dem Buch der Lieder und Gedichte (Shijing–Guofeng). YinYang Media Verlag, Kelkheim. In German; ISBN: 9783935727129;. [find](https://scholar.google.com/scholar?q=Hans%2DG%C3%BCnter+Wagner%2E+2007%2E+Hell+ein+Vogelruf+ert%C3%B6nt%3A+Altchinesische+Volkslyrik+aus+dem+Buch+der+Lieder+und+Gedichte+%28Shijing%E2%80%93Guofeng%29%2E+YinYang+Media+Verlag%2C+Kelkheim%2E+In+German%3B+ISBN%3A+9783935727129%3B%2E)
62. Chen Zhi. 2007. The Shaping of the Book of Songs: From Ritualization to Secularization. Steyler Verlag, Nettetal. [find](https://scholar.google.com/scholar?q=Chen+Zhi%2E+2007%2E+The+Shaping+of+the+Book+of+Songs%3A+From+Ritualization+to+Secularization%2E+Steyler+Verlag%2C+Nettetal%2E)
63. Arthur Waley. 1937. The Book of Songs. Houghton Mifflin Company, Boston. [find](https://scholar.google.com/scholar?q=Arthur+Waley%2E+1937%2E+The+Book+of+Songs%2E+Houghton+Mifflin+Company%2C+Boston%2E)
64. Shanshan Wang, Derek Wong, Jingming Yao, and Lidia Chao. 2024. What is the best way for chatgpt to translate poetry? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14025– 14043. [find](https://scholar.google.com/scholar?q=Shanshan+Wang%2C+Derek+Wong%2C+Jingming+Yao%2C+and+Lidia+Chao%2E+2024%2E+What+is+the+best+way+for+chatgpt+to+translate+poetry%3F+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computational+Ling)
65. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, and others. 2020. [Transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, pages 38–45.
66. Yuanchong Xu. 1993. Book of poetry (诗经). Hunan Publishing House, Changsha. In Chinese and English; ISBN: 7543806878;. [find](https://scholar.google.com/scholar?q=Yuanchong+Xu%2E+1993%2E+Book+of+poetry+%28%E8%AF%97%E7%BB%8F%29%2E+Hunan+Publishing+House%2C+Changsha%2E+In+Chinese+and+English%3B+ISBN%3A+7543806878%3B%2E)
67. Zhenfu Zhou. 2013. Translation and Annotation of the Book of Songs (诗经译注). Zhonghua Book Company, Beijing. In Chinese; ISBN: 9787101093414;. [find](https://scholar.google.com/scholar?q=Zhenfu+Zhou%2E+2013%2E+Translation+and+Annotation+of+the+Book+of+Songs+%28%E8%AF%97%E7%BB%8F%E8%AF%91%E6%B3%A8%29%2E+Zhonghua+Book+Company%2C+Beijing%2E+In+Chinese%3B+ISBN%3A+9787101093414%3B%2E)
68. Xi Zhu. 2011. Collected Commentaries on the Book of Songs (诗集传). Zhonghua Book Company, Beijing. In Chinese; ISBN: 9787101077162;. [find](https://scholar.google.com/scholar?q=Xi+Zhu%2E+2011%2E+Collected+Commentaries+on+the+Book+of+Songs+%28%E8%AF%97%E9%9B%86%E4%BC%A0%29%2E+Zhonghua+Book+Company%2C+Beijing%2E+In+Chinese%3B+ISBN%3A+9787101077162%3B%2E)

*Updated 1 November 2026*