摘要：
学习一下inside-outside算法，主要用于在已知文法结构下CFG，无监督parse。CFG可定义为Chomsky Normal Form，对于生成的任何一个分析树有对应的potential值，树的potential值由其生成规则的potential值之乘积。因此对于potential的不同定... 阅读全文
摘要：
回顾一些参数估计的方法，包括梯度下降算法和牛顿法及其扩展梯度下降算法(Gradient Descent, GD)目的是优化参数，使得估计值与真实值的误差最小。试用于优化目标形式为:其中表示特征权重，表示样本的以维特征描述，为样本。1, 批梯度下降算法(batch gradient decent, B... 阅读全文
摘要：
Relation ExtractionA set of major relation types and their subtypes are defined by ACE (short for Annotation Context Extraction). ACE makes a distinct... 阅读全文
摘要：
Information extraction in this chapter mainly focuses on named entities recognition and relation extractionIntroductionE.g. in 1998, Larry Page and Se... 阅读全文
摘要：
IntroductionData mining can learn interesting patterns from the data in a dynamic and scalable way. Information retrieval has traditionally focused mo... 阅读全文
摘要：
The economist as scientistEconomist approach study of economy in much the same way as a physicist approaches the study of matter and a biologist appro... 阅读全文
摘要：
Ten principlesHow people make decisions1,people face tradeoffsThereis no such thing as a free lunch. Making decisions requires trading off onegoal aga... 阅读全文