1) error-driven learning
错误驱动学习
1.
This paper proposes a new method for recognizing the extents of the time expressions based on dependency parsing and error-driven learning,which begins with time trigger word(namely,the syntactic head of dependency relation),uses Chinese dependency parsing to recognize the extents of the time expressions,Subsequently,we use the transformation-based error-driven lear.
首先以时间触发词为切入点,据依存关系递归地识别时间表达式,大大地提高了识别效果;然后,采用错误驱动学习来进一步增强识别效果,根据错误识别结果和人工标注的差异自动地获取和改进规则,使系统的性能又提高了近3。
2.
This paper proposes a chunking approach that combines support vector machine with error-driven learning.
给出了一种错误驱动学习机制与SVM相结合的汉语组块识别方法。
3.
This paper proposes a new method for recognizing the extents of the time expressions based on the dependency parsing and error-driven learning,which begins with time trigger word(namely,the syntactic head of dependency relation),uses Chinese dependency parsing to recognize the extents of the time expressions,and greatly improves the system performance;Subsequently,we .
首先以时间触发词为切入点,据依存关系递归地识别时间表达式,大大地提高了识别效果：然后,采用错误驱动学习来进一步增强识别效果,根据错误识别结果和人工标注的差异自动地获取和改进规则,使系统的性能又提高了近3。
2) transformation-based error-driven learning
基于转换的错误驱动学习
1.
The paper presents a method of Chinese chunk recognition based on Support Vector Machines(SVM) and transformation-based error-driven learning.
本文研究了一种支持向量机(SVM)和基于转换的错误驱动学习相结合的汉语组块识别方法。
2.
Chinese name identification based on Support Vector Machines(SVM) and is corrected by transformation-based error-driven learning.
利用基于转换的错误驱动学习方法对SVM的识别结果进行校正,转换规则较好地处理了语言现象中的特殊情况,进一步提高了SVM的识别结果。
3) transformation-based error-drive learning
基于转换的错误驱动学习方法
4) Transformation-based Error Driven Learning
基于转换的错误驱动学习算法
5) error-driven
错误驱动
1.
This paper adopts three methods including Error-Driven,Support Vector Machines and Hidden Markov Model to recognize noun phrases in Chinese texts.
利用错误驱动法、支持向量机法和隐马尔可模型3种方法对汉语文本进行名词短语识别,对实验进行比较分析,结果表明SVM与HMM的识别效果总体上要好于错误驱动法,HMM法在封闭测试中优势明显。
2.
Using three methods of error-driven,support vector machine and hidden markov model,noun phrase recognition is carried on to chinese text,through comparative analysis to experiment,the results indicate that the recognition effects of SVM and HMM are overall better than the method of error-driven,HMM method has the distinct advantage in the closed test.
利用错误驱动法、支持向量机法和隐马尔可模型三种方法对汉语文本进行名词短语识别,对实验进行比较分析,结果表明SVM与HMM的识别效果总体上要好于错误驱动法,HMM法在封闭测试中优势明显。
3.
This paper proposes a hybrid error-driven combination approach to chunking Chinese Base noun phrase(Chinese Base NP),which combines TBL(Transformation-based Learning) model and CRF(Conditional Random Field) model.
本文采用一种新的错误驱动的组合分类器方法来实现中文Base NP识别。
6) learning mistakes
学习错误
补充资料：尝试错误学习
尝试错误学习
trial and error learning
尝试错误学习(trial and error learning)美国心理学家E.L.桑代克通过动物实验加以验证的并在理论上进行阐述的一种学习方式。他认为，学习是一种渐进的、尝试与错误和偶然成功的过程。学习者在学习过程中，会发生或多或少的错误反应，间或也会出现正确反应，通过必要的、反复的尝试练习，使正确反应逐渐增强、错误反应逐渐减弱，直至学习成功。所要解决的问题错综复杂而不易察觉，刺激情境模糊而混乱，采取何种反应方式为宜又不清楚，这一切是发生尝试错误学习的条件。J.M.索里和C.W.特尔福德在《教育心理学》一书中指出，尝试错误学习包含动机、问题、可变性反应、偶然成功、淘汰与选择、整合与协调等因素。 (成立夫撰}巫查国审)
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条