MCORES: a system for noun phrase coreference resolution for clinical records.
MCORES: a system for noun phrase coreference resolution for clinical records.
复制标题
MCORES：临床记录名词短语共指解析系统。
DOI：
10.1136/amiajnl-2011-000591
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Uzuner,Ozlem
中科院分区：
文献类型：
--
作者：
Bodnari,Andreea;Szolovits,Peter;Uzuner,Ozlem
目的电子病历的描述包含对临床实践和多用途研究有用的信息。在自动化系统可以使用这些信息之前，需要将其放入结构化形式。共指消解是将叙述转化为结构化形式的一个步骤。方法本研究提出了一个针对四个临床常用语义类别：人、问题、治疗和测试的名词短语的医学共指消解系统。MCORES将共指关系解析视为二进制分类任务。给定语义范畴中的一对概念，它确定共指对并将它们聚类成链。MCORES使用一组增强的词汇、语法和语义特性。结果和结论MCORES与只使用单一视角的“令牌重叠”和“数字一致”特征的内部基线进行了比较。结果表明，MCORES的性能优于基准；其增强的功能对性能有很大贡献。除了基准之外，MCORES还与两个可用的第三方开放域系统RECONCILEACL09和美丽的回指解析工具包(BART)进行了比较。在临床记录上，MCORES的表现优于这两种系统。
ObjectiveNarratives of electronic medical records contain information that can be useful for clinical practice and multi-purpose research. This information needs to be put into a structured form before it can be used by automated systems. Coreference resolution is a step in the transformation of narratives into a structured form.MethodsThis study presents a medical coreference resolution system (MCORES) for noun phrases in four frequently used clinical semantic categories: persons, problems, treatments, and tests. MCORES treats coreference resolution as a binary classification task. Given a pair of concepts from a semantic category, it determines coreferent pairs and clusters them into chains. MCORES uses an enhanced set of lexical, syntactic, and semantic features. Some MCORES features measure the distance between various representations of the concepts in a pair and can be asymmetric.Results and ConclusionMCORES was compared with an in-house baseline that uses only single-perspective ‘token overlap’ and ‘number agreement’ features. MCORES was shown to outperform the baseline; its enhanced features contribute significantly to performance. In addition to the baseline, MCORES was compared against two available third-party, open-domain systems, RECONCILEACL09and the Beautiful Anaphora Resolution Toolkit (BART). MCORES was shown to outperform both of these systems on clinical records.