We put forward a novel question classification hierarchy which is based on answer type and question pattern. It retains the semantic and structured information of questions.
我们提出了一种基于答案类型与问题模式的问题分类体系,同时保留了问题的语义信息与结构信息。
It makes question classification model from the existing knowledge base by using machine learning.
它是利用机器学习的方法,从已存在的知识库中构造出问题分类模型。
This paper mainly focuses on question analysis and answer extraction. Question analysis includes question classification, keyword extraction and keyword expansion.
本文主要研究了问答系统的问题理解与答案抽取两个部分。
This method can improve the precision of question classification: the classification precision of coarse classes and fine classes reaches 92.18% and 83.86% respectively.
该方法能显著地提高问题分类的精度,大类和小类的分类精度分别达到了92.18%和83.86%。
Taking the semantic information of questions as a criterion of question classification, a new classification system is proposed, and then a HowNet based automatic classification approach is presented.
以问题的语义信息为分类依据,建立了一个新的问题分类体系,并提出了一种基于《知网》的自动分类方法。
The experiment result show that this method can improve the precision of question classification: the classification precision of coarse classes and fine classes reaches 90.75% and 79.8% respectively.
实验结果表明,该方法能有效提高问题分类的精度,大类和小类的分类精度分别达到了90.75%和79.8%。
Question classification is the basis of a question-answering system.
问题分类是问答系统处理的基础。
Question classification is an important component of the question answering system, its result directly influences the performance of the question answering system.
问题分类是问答系统中重要的组成部分,问题分类结果的好坏直接影响问答系统的性能。
Question classification is an important component of the question answering system, its result directly influences the performance of the question answering system.
问题分类是问答系统中重要的组成部分,问题分类结果的好坏直接影响问答系统的性能。
应用推荐