利用自然语言处理技术从生命之树的分类描述中提取表型特征。
Extraction of phenotypic traits from taxonomic descriptions for the tree of life using natural language processing.
作者信息
Endara Lorena, Cui Hong, Burleigh J Gordon
机构信息
Department of Biology University of Florida Gainesville Florida 32611 USA.
School of Information University of Arizona Tucson Arizona 85719 USA.
出版信息
Appl Plant Sci. 2018 Mar 31;6(3):e1035. doi: 10.1002/aps3.1035. eCollection 2018 Mar.
PREMISE OF THE STUDY
Phenotypic data sets are necessary to elucidate the genealogy of life, but assembling phenotypic data for taxa across the tree of life can be technically challenging and prohibitively time consuming. We describe a semi-automated protocol to facilitate and expedite the assembly of phenotypic character matrices of plants from formal taxonomic descriptions. This pipeline uses new natural language processing (NLP) techniques and a glossary of over 9000 botanical terms.
METHODS AND RESULTS
Our protocol includes the Explorer of Taxon Concepts (ETC), an online application that assembles taxon-by-character matrices from taxonomic descriptions, and MatrixConverter, a Java application that enables users to evaluate and discretize the characters extracted by ETC. We demonstrate this protocol using descriptions from Araucariaceae.
CONCLUSIONS
The NLP pipeline unlocks the phenotypic data found in taxonomic descriptions and makes them usable for evolutionary analyses.
研究前提
表型数据集对于阐明生命谱系至关重要，但为生命之树上的各类群收集表型数据在技术上具有挑战性且耗时极长。我们描述了一种半自动化方案，以促进和加速从正式分类描述中组装植物表型特征矩阵。该流程使用了新的自然语言处理（NLP）技术和一个包含9000多个植物学术语的词汇表。
方法与结果
我们的方案包括分类群概念浏览器（ETC），这是一个在线应用程序，可从分类描述中组装分类群×特征矩阵，以及矩阵转换器（MatrixConverter），这是一个Java应用程序，可让用户评估和离散化由ETC提取的特征。我们使用南洋杉科的描述来演示此方案。
结论
NLP流程解锁了分类描述中发现的表型数据，并使其可用于进化分析。
Zotero 插件