Extracting Agricultural Experts' Experiential Knowledge from Non-Standardized Text with Quantity and Operation Scope Constraints

Shigang Liu; Huarui Wu; Jialong Huang

doi:10.62762/TIS.2026.540629

Article Information

Published in ICCK Transactions on Intelligent Systematics

Volume/Issue Volume 3, Issue 4, 2026

Pages 229-244

Abstract

Expert advice on crop management is often written informally, and in such text a number can easily be assigned the wrong role or attached to the wrong operation, material, or measurement basis. We propose QS-IE, a knowledge extraction method constrained by quantity and operation scope. Its unit of extraction is a complete quantitative fact. Given a shared set of numeric candidates and a single base model, QS-IE selects complete candidates from several prompting strategies, verifies them against the source text, and applies scope constraints, so that every extracted quantity stays linked to its source evidence. We built a corpus of 4006 texts on tomato cultivation. Two researchers with agronomy backgrounds jointly annotated and reviewed 1000 of them; the other 3006 were annotated with large language model assistance and then reviewed by hand. The corpus was split into 3206 development texts and 800 independent test texts. On the 1152 reference facts of the test set, QS-IE reached a precision of 84.02%, a recall of 86.72%, and a micro-averaged F1 of 85.35%, which is 3.91 percentage points higher than the strongest baseline, a multi-strategy in-context learning ensemble. Removing the operation scope constraints lowered test F1 by 8.24 percentage points. In a sampled human audit of the test set, 82.00% of the outputs for texts containing target facts were judged usable, and all six engineering checks on storage and evidence traceability were passed. The results indicate that explicit association constraints make quantitative facts extracted from tomato cultivation texts more complete and easier to review, which supports the structured, traceable storage of experiential knowledge that experts express in non-standardized text.

Graphical Abstract

Extracting Agricultural Experts' Experiential Knowledge from Non-Standardized Text with Quantity and Operation Scope Constraints

Keywords

agricultural expert knowledge non-standardized advice knowledge extraction numeric roles operation scope evidence traceability

Data Availability Statement

The corpus, annotation files, and extraction code produced in this study are not publicly available, as the source materials are subject to copyright and the terms of the platforms from which they were collected. The method configurations, random seeds, and model identifiers are reported in full in the Methodology section to support reproducibility of the extraction pipeline. Readers seeking further information may contact the corresponding author.

Funding

This work was supported by the National Major Agricultural Science and Technology Project under Grant 0304.

Conflicts of Interest

The authors declare no conflicts of interest.

AI Use Statement

The authors declare that GPT-6.1 Sol was used for language editing and translation of the manuscript. The authors have carefully reviewed, revised, and verified the AI-assisted output and take full responsibility for the content of the manuscript.

Ethical Approval and Consent to Participate

This study involved no human or animal experiments. The source texts used for corpus construction are publicly available and contain no private or sensitive information. The researchers who participated in annotation and quality auditing provided informed consent; their contributions were used solely for the analysis and publication described in this study, and no personal data were collected or retained beyond what was necessary for annotation review. No clinical intervention, deception, or collection of personal data from third parties was involved. This study was therefore exempt from formal ethical review in accordance with applicable institutional guidelines.

References

Rafea, A., El-Dessouki, A., Hassan, H., & Mohamed, S. (1993). Development and implementation of a knowledge acquisition methodology for crop management expert systems. Computers and electronics in agriculture, 8(2), 129-146.
[CrossRef] [Google Scholar]
Girard, N., & Hubert, B. (1999). Modelling expert knowledge with knowledge-based systems to design decision aids: The example of a knowledge-based model on grazing management. Agricultural Systems, 59(2), 123-144.
[CrossRef] [Google Scholar]
Cornelissen, A. M. G., van den Berg, J., Koops, W. J., & Kaymak, U. (2003). Elicitation of expert knowledge for fuzzy evaluation of agricultural production systems. Agriculture, ecosystems & environment, 95(1), 1-18.
[CrossRef] [Google Scholar]
Robledo, J., Sulá, A. I. P., Jaworski, L. G., Mouafo-Tchinda, R. A., Andersen Onofre, K. F., Thomas-Sharma, S., & Garrett, K. A. (2025). Expert knowledge elicitation: Accessing the big data in experts’ brains. Phytopathology®, 115(10), 1245-1259.
[CrossRef] [Google Scholar]
Semeon, G., & Garfield, M. J. (2019). Framework for externalization of tacit knowledge in participatory agricultural research in Ethiopia: The case of Farmers Research Group (FRG). In Proceedings of the 52nd Hawaii International Conference on System Sciences (pp. 5339-5347). https://aisel.aisnet.org/hicss-52/ks/culture_ks/4/
[Google Scholar]
Koenderink, N. J., Top, J. L., & van Vliet, L. J. (2005, August). Expert-based ontology construction: A case-study in horticulture. In 16th International Workshop on Database and Expert Systems Applications (DEXA'05) (pp. 383-387). IEEE.
[CrossRef] [Google Scholar]
Ngo, Q. H., Kechadi, T., & Le-Khac, N. A. (2022). Knowledge representation in digital agriculture: A step towards standardised model. Computers and Electronics in Agriculture, 199, 107127.
[CrossRef] [Google Scholar]
Jonquet, C., Toulet, A., Arnaud, E., Aubin, S., Yeumo, E. D., Emonet, V., ... & Larmande, P. (2018). AgroPortal: A vocabulary and ontology repository for agronomy. Computers and Electronics in Agriculture, 144, 126-143.
[CrossRef] [Google Scholar]
Nismi Mol, E. A., & Santosh Kumar, M. B. (2023). Review on knowledge extraction from text and scope in agriculture domain. Artificial intelligence review, 56(5), 4403-4445.
[CrossRef] [Google Scholar]
Wu, H., Xie, N., Fan, J., Wang, X., Liu, H., Zheng, H., ... & Lv, Q. (2026). Autonomous construction of crop pest and disease knowledge graphs at scale via LLM-driven expert modeling. Computers and Electronics in Agriculture, 250, 111970.
[CrossRef] [Google Scholar]
Guo, W., & Zhao, C. (2026). Wheat agronomic knowledge extraction and spatio-temporal knowledge graph construction. Applied Sciences, 16(10), 4776.
[CrossRef] [Google Scholar]
Wang, Y., Zhao, K., Li, H., Wang, R., & Chen, W. (2026). A condition-aware retrieval-augmented decision support framework for tomato cultivation management. Frontiers in Plant Science, 17, 1802748.
[CrossRef] [Google Scholar]
Gu, W., Wang, X., Wang, Z., Gao, Y., Zhang, X., Zheng, J., & Liu, K. (2026). PlantExpert: A knowledge graph-augmented large language model for agricultural question answering. Smart Agricultural Technology, 15, 102467.
[CrossRef] [Google Scholar]
Wu, H., Xie, N., Wang, X., Fan, J., Li, Y., & Meng, Z. (2025). Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection. Frontiers in Plant Science, 16, 1696872.
[CrossRef] [Google Scholar]
Lu, Y., Liu, Q., Dai, D., Xiao, X., Lin, H., Han, X., ... & Wu, H. (2022, May). Unified structure generation for universal information extraction. In Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: Long papers) (pp. 5755-5772).
[CrossRef] [Google Scholar]
Wadden, D., Wennberg, U., Luan, Y., & Hajishirzi, H. (2019, November). Entity, relation, and event extraction with contextualized span representations. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP) (pp. 5784-5789).
[CrossRef] [Google Scholar]
Kaushik, N., & Chatterjee, N. (2018). Automatic relationship extraction from agricultural text for ontology construction. Information processing in agriculture, 5(1), 60-73.
[CrossRef] [Google Scholar]
Dagdelen, J., Dunn, A., Lee, S., Walker, N., Rosen, A. S., Ceder, G., ... & Jain, A. (2024). Structured information extraction from scientific text with large language models. Nature communications, 15(1), 1418.
[CrossRef] [Google Scholar]
Polak, M. P., & Morgan, D. (2024). Extracting accurate materials data from research papers with conversational language models and prompt engineering. Nature Communications, 15(1), 1569.
[CrossRef] [Google Scholar]
Mysore, S., Jensen, Z., Kim, E., Huang, K., Chang, H. S., Strubell, E., ... & Olivetti, E. (2019, August). The materials science procedural text corpus: Annotating materials synthesis procedures with shallow semantic structures. In Proceedings of the 13th linguistic annotation workshop (pp. 56-64).
[CrossRef] [Google Scholar]
Du, W., Liao, W., Liang, H., & Lei, W. (2024, August). PAGED: A benchmark for procedural graphs extraction from documents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 10829-10846).
[CrossRef] [Google Scholar]
Ying, W., Liu, Y., Zhao, X., Cheng, W., Chen, Z., Yu, W., Fu, Y., & Chen, H. (2026). Multi-agent procedural graph extraction with structural and logical refinement. In Findings of the Association for Computational Linguistics: EACL 2026 (pp. 3021-3034).
[CrossRef] [Google Scholar]
Liu, J., Shen, D., Zhang, Y., Dolan, W. B., Carin, L., & Chen, W. (2022, May). What makes good in-context examples for GPT-3?. In Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd workshop on knowledge extraction and integration for deep learning architectures (pp. 100-114).
[CrossRef] [Google Scholar]
Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., ... & Piao, Y. (2024). Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437.
[CrossRef] [Google Scholar]
Court, C. J., & Cole, J. M. (2018). Auto-generated materials database of Curie and Néel temperatures via semi-supervised relationship extraction. Scientific data, 5(1), 180111.
[CrossRef] [Google Scholar]
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33, 9459-9474. https://papers.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html
[Google Scholar]
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877-1901. https://proceedings.neurips.cc/paper_files/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
[Google Scholar]
Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., Zhang, L., ... & Lin, J. (2024). Qwen2.5-coder technical report. arXiv preprint arXiv:2409.12186.
[CrossRef] [Google Scholar]
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information processing & management, 45(4), 427-437.
[CrossRef] [Google Scholar]
Buneman, P., Khanna, S., & Wang-Chiew, T. (2001, January). Why and where: A characterization of data provenance. In International conference on database theory (pp. 316-330). Berlin, Heidelberg: Springer Berlin Heidelberg.
[CrossRef] [Google Scholar]
Artstein, R., & Poesio, M. (2008). Inter-coder agreement for computational linguistics. Computational linguistics, 34(4), 555-596.
[CrossRef] [Google Scholar]
Arora, S., Narayan, A., Chen, M. F., Orr, L., Guha, N., Bhatia, K., ... & Ré, C. (2022). Ask me anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441.
[CrossRef] [Google Scholar]
Ballot, R., Loyce, C., Jeuffroy, M.-H., Ronceux, A., Gombert, J., Lesur-Dumoulin, C., & Guichard, L. (2018). First cropping system model based on expert-knowledge parameterization. Agronomy for Sustainable Development, 38, 33.
[CrossRef] [Google Scholar]
Buche, P., Cuq, B., Fortin, J., & Sipieter, C. (2019). Expertise-based decision support for managing food quality in agri-food companies. Computers and Electronics in Agriculture, 163, 104843.
[CrossRef] [Google Scholar]

Cite This Article

APA Style

Liu, S., Wu, H., & Huang, J. (2026). Extracting Agricultural Experts' Experiential Knowledge from Non-Standardized Text with Quantity and Operation Scope Constraints. ICCK Transactions on Intelligent Systematics, 3(4), 229-244. https://doi.org/10.62762/TIS.2026.540629

Export Citation

RIS Format

Compatible with EndNote, Zotero, Mendeley, and other reference managers

TY  - JOUR
AU  - Liu, Shigang
AU  - Wu, Huarui
AU  - Huang, Jialong
PY  - 2026
DA  - 2026/10/26
TI  - Extracting Agricultural Experts' Experiential Knowledge from Non-Standardized Text with Quantity and Operation Scope Constraints
JO  - ICCK Transactions on Intelligent Systematics
T2  - ICCK Transactions on Intelligent Systematics
JF  - ICCK Transactions on Intelligent Systematics
VL  - 3
IS  - 4
SP  - 229
EP  - 244
DO  - 10.62762/TIS.2026.540629
UR  - https://www.icck.org/article/abs/TIS.2026.540629
KW  - agricultural expert knowledge
KW  - non-standardized advice
KW  - knowledge extraction
KW  - numeric roles
KW  - operation scope
KW  - evidence traceability
AB  - Expert advice on crop management is often written informally, and in such text a number can easily be assigned the wrong role or attached to the wrong operation, material, or measurement basis. We propose QS-IE, a knowledge extraction method constrained by quantity and operation scope. Its unit of extraction is a complete quantitative fact. Given a shared set of numeric candidates and a single base model, QS-IE selects complete candidates from several prompting strategies, verifies them against the source text, and applies scope constraints, so that every extracted quantity stays linked to its source evidence. We built a corpus of 4006 texts on tomato cultivation. Two researchers with agronomy backgrounds jointly annotated and reviewed 1000 of them; the other 3006 were annotated with large language model assistance and then reviewed by hand. The corpus was split into 3206 development texts and 800 independent test texts. On the 1152 reference facts of the test set, QS-IE reached a precision of 84.02%, a recall of 86.72%, and a micro-averaged F1 of 85.35%, which is 3.91 percentage points higher than the strongest baseline, a multi-strategy in-context learning ensemble. Removing the operation scope constraints lowered test F1 by 8.24 percentage points. In a sampled human audit of the test set, 82.00% of the outputs for texts containing target facts were judged usable, and all six engineering checks on storage and evidence traceability were passed. The results indicate that explicit association constraints make quantitative facts extracted from tomato cultivation texts more complete and easier to review, which supports the structured, traceable storage of experiential knowledge that experts express in non-standardized text.
SN  - 3068-5079
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  -

BibTeX Format

Compatible with LaTeX, BibTeX, and other reference managers

@article{Liu2026Extracting,
  author = {Shigang Liu and Huarui Wu and Jialong Huang},
  title = {Extracting Agricultural Experts' Experiential Knowledge from Non-Standardized Text with Quantity and Operation Scope Constraints},
  journal = {ICCK Transactions on Intelligent Systematics},
  year = {2026},
  volume = {3},
  number = {4},
  pages = {229-244},
  doi = {10.62762/TIS.2026.540629},
  url = {https://www.icck.org/article/abs/TIS.2026.540629},
  abstract = {Expert advice on crop management is often written informally, and in such text a number can easily be assigned the wrong role or attached to the wrong operation, material, or measurement basis. We propose QS-IE, a knowledge extraction method constrained by quantity and operation scope. Its unit of extraction is a complete quantitative fact. Given a shared set of numeric candidates and a single base model, QS-IE selects complete candidates from several prompting strategies, verifies them against the source text, and applies scope constraints, so that every extracted quantity stays linked to its source evidence. We built a corpus of 4006 texts on tomato cultivation. Two researchers with agronomy backgrounds jointly annotated and reviewed 1000 of them; the other 3006 were annotated with large language model assistance and then reviewed by hand. The corpus was split into 3206 development texts and 800 independent test texts. On the 1152 reference facts of the test set, QS-IE reached a precision of 84.02\%, a recall of 86.72\%, and a micro-averaged F1 of 85.35\%, which is 3.91 percentage points higher than the strongest baseline, a multi-strategy in-context learning ensemble. Removing the operation scope constraints lowered test F1 by 8.24 percentage points. In a sampled human audit of the test set, 82.00\% of the outputs for texts containing target facts were judged usable, and all six engineering checks on storage and evidence traceability were passed. The results indicate that explicit association constraints make quantitative facts extracted from tomato cultivation texts more complete and easier to review, which supports the structured, traceable storage of experiential knowledge that experts express in non-standardized text.},
  keywords = {agricultural expert knowledge, non-standardized advice, knowledge extraction, numeric roles, operation scope, evidence traceability},
  issn = {3068-5079},
  publisher = {Institute of Central Computation and Knowledge}
}

Article Metrics

Citations

Crossref

0

Scopus

0

Views

20

PDF Downloads

5

Publisher's Note

ICCK stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and Permissions

Copyright © 2026 by the Author(s). Published by Institute of Central Computation and Knowledge. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

ICCK Transactions on Intelligent Systematics

ISSN: 3068-5079 (Online) | ISSN: 3069-003X (Print)

[email protected]

Preserved at
Portico

User

Unlimited Downloads

Complete Library Access

Membership Eligibility

Community Leadership Opportunities