【摘 要】
：
为了完善中文时间信息标注规范,实现中文时间短语的自动标注,该文研究并修改国际通用的时间短语标注规范TIMEX2的中文标注草案,以此为基础开发一个基于正则表达式的中文TIMEX
论文部分内容阅读
为了完善中文时间信息标注规范,实现中文时间短语的自动标注,该文研究并修改国际通用的时间短语标注规范TIMEX2的中文标注草案,以此为基础开发一个基于正则表达式的中文TIMEX2自动标注系统(CTAT).该系统采用3层候选确定参考时间,并行使用多个模块识别输入句子中的时间短语,通过排序冲突消解确定最终结果.经测试,该系统识别时间短语和将时间信息值解析为标准格式的F-measure分别达到了90.15%和83.27%, 与其他语言同类系统性能相当.应用该系统标注的语料,为时间信息处理方面的后续研究提供了重要资源.
其他文献
为了解国内外航空航天类科技期刊英文摘要写作的现状,统计并分析了8种国内外中英文期刊英文摘要的长度及时态和语态的使用特点。统计结果表明,国内期刊英文摘要长度普遍比国
为探究吕家坨井田地质构造格局,根据钻孔勘探资料,采用分形理论和趋势面分析方法,研究了井田7
In this article, we introduce the Hausdorff convergence to derive a differentiable sphere theorem which shows an interesting rigidity phenomenon on some kind of
Temporal relation classification is one of contemporary demanding tasks of natural language processing. This task can be used in various applications such as qu
Based on QoS (quality of service) parameters: time delay, jitter, bandwidth and package loss. As time delay in the Internet is variable, it is hard to compensat
Adopting the regression SVM framework, this paper proposes a linguistically motivated feature engineering strategy to develop an MT evaluation metric with a bet
Multiway Decision Graphs (MDGs) are a canonical representation of a subset of many-sorted first-order logic. This subset generalizes the logic of equality with
基于网格资源的异构性和不同所有权现象,为满足中国教育科研网格监控子项目CGSV(chinagrid supervision)中用户的模糊监控需求,提出一种基于语义关联的网格监控元数据管理方
Today steel is produced by two steelmaking processes,the basic oxygen furnace and the electric arc furnace. Three types of iron input materials for both process
Objective To review articles aiming to present an overview of the principles,progress,uses and limitations of laser speckle flowgraphy (LSFG) in posterior fundu