Making floras computable:Audited translation of flora of China as reusable taxonomic knowledgeOA
Floras and monographs are among the most information-dense syntheses in taxonomy,but they were written primarily for expert reading rather than computational reuse.In Large Language Model(LLM)-assisted translation,the most consequential failures are often small:a measurement range may be simplified,a unit or special symbol may be changed,a negation cue may be lost,or a name string may no longer be stable enough for linking.
Bin-Bin Liu;Fang-Zhe Ai;Chen-Yang Liao;Chao Xu;Hai-Rui Luo;Jing Xuan;Yi-Gang Song;Min Li
Key Laboratory of Systematic and Evolutionary Botany/State Key Laboratory of Plant Diversity and Specialty Crops,Institute of Botany,Chinese Academy of Sciences,Beijing 100093,China China National Botanical Garden,Beijing 100093,ChinaBeijing Baidu Netcom Science Technology Co.,Ltd.,No.10 Shangdi 10th Street,Beijing 100085,ChinaCollege of Architecture and Environment,Sichuan University,Chengdu 610065,ChinaKey Laboratory of Systematic and Evolutionary Botany/State Key Laboratory of Plant Diversity and Specialty Crops,Institute of Botany,Chinese Academy of Sciences,Beijing 100093,China China National Botanical Garden,Beijing 100093,ChinaBig Data and AI Biodiversity Conservation Research Center,Institute of Botany,Chinese Academy of Sciences,Beijing 100093,ChinaBig Data and AI Biodiversity Conservation Research Center,Institute of Botany,Chinese Academy of Sciences,Beijing 100093,ChinaKey Laboratory of National Forestry and Grassland Administration on East China Plant Conservation and Utilization,Shanghai Chenshan Botanical Garden,Shanghai 201602,ChinaBig Data and AI Biodiversity Conservation Research Center,Institute of Botany,Chinese Academy of Sciences,Beijing 100093,China
农业科技
FlorasTaxonomic descriptionsLarge language modelsTerminology alignmentAuditVersioning
《Plant Diversity》 2026 (4)
P.855-859,5
supported by the National Natural Science Foundation of China(grant numbers 32570240 to B.B.L.,32270216 to B.B.L.,and 32000163 to B.B.L.)the Youth Innovation Promotion Association CAS(2023086 to B.B.L.)the Biological Resources Programme,Chinese Academy of Sciences(CAS-TAX-24-013 to B.B.L.).
评论