Hahn U, Schnattinger K, Romacker M
Text Knowledge Engineering Lab, Freiburg University, Germany.
Proc AMIA Annu Fall Symp. 1996:383-7.
An approach to knowledge-based understanding of realistic texts from the medical domain (viz. findings of gastro-intestinal diseases) is presented. We survey major methodological features of an object-oriented, fully lexicalized, dependency-based grammar model which is tightly linked to domain knowledge representations based on description logics. The parser adheres to the principles of robustness, incrementality and concurrency. The substrate of automatic knowledge acquisition are text knowledge bases generated by the parser from medical narratives, which represent major portions of the content of these documents.
本文提出了一种基于知识理解医学领域现实文本（即胃肠疾病的检查结果）的方法。我们概述了一种面向对象、完全词汇化、基于依存关系的语法模型的主要方法特征，该模型与基于描述逻辑的领域知识表示紧密相连。该解析器遵循稳健性、增量性和并发性原则。自动知识获取的基础是解析器从医学叙述中生成的文本知识库，这些知识库代表了这些文档内容的主要部分。
