%0 Journal Article
%T A Multi-level Disambiguation Framework for Gene Name Normalization<br>一种用于基因名字规范化的多层歧义消解框架
%A SUN Cheng-Jie
%A WANG Xiao-Long
%A LIN Lei
%A LIU Yuan-Chao
%A <br>孙承杰
%A 王晓龙
%A 林磊
%A 刘远超
%J 自动化学报
%D 2009
%I 
%X The flexible nomenclature of gene name results in severe semantic ambiguity, which is an obstacle for deep biomed-ical text mining. Gene name normalization (GN) is an effective way to resolve this problem. In this work, a multi-level disam-biguation framework was proposed to solve gene name normal-ization problem. Aiming at different ambiguity situations during the procedure of GN, three different strategies were included in the framework. They were dictionary-based gene name detec-tion, machine-learning-based candidate seleetion, and semantic-based disambiguation. Experimental results showed that the proposed method could achieve 0.746 F-measure on the BioCre-AtlvE2006 GN task test data set.
%K Gene name normalization (GN)
%K maximum en-tropy model
%K semantic similarity<br>基因名字规范化
%K 最大熵模型
%K 语义相似度
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=DB7F4D8C762377EA37C0C83AC8702439&yid=DE12191FBD62783C&vid=6209D9E8050195F5&iid=0B39A22176CE99FB&sid=23104246A5FCFCEF&eid=2BA123C6EB9D54C2&journal_id=0254-4156&journal_name=自动化学报&referenced_num=1&reference_num=0