QA system contains three main procedures: question understanding, information retrieve and answer extraction. 问答系统中包括三个主要的部分:问题理解,信息检索和答案抽取。
Research of Answer Extraction in Question Answering System Based on Admission Counseling 基于招生咨询域的问答系统中答案抽取的研究
An efficient answer extraction system named Dependency Inspection based AE System ( DIAES) was proposed to improve the accuracy of locating candidate answers. 为了提高答案抽取应用中定位候选答案的准确性,提出了一种基于依存语义检测的答案抽取应用系统(DIAES)。
The Research of Answer Extraction Algorithm in Chinese Question and Answering System 中文问答系统中的答案抽取算法研究
Improved Answer Extraction Method Based on Pattern Matching 改进的基于模式匹配的答案抽取方法
An Approach to Answer Extraction in Question Answering Based on Semantic Concept 问答系统中基于语义概念的问题答案形成方法研究
The VIC system consists of five sub-systems: Question analyzer, Search engine, Document processing, Answer extraction. 虚拟信息系统按其结构可以分为问题理解、搜索引擎、结果处理、问题回答FAQ五个子系统。
In answer extraction module HMM based Named Entity Recognition is used. 答案的抽取使用了基于隐马尔可夫模型的命名实体识别算法。
A Web-based Chinese question answering system is made of four parts: question processing, information retrieval, answer extraction and answer justification. It utilizes named entity recognition, semantic dependency relations and case-based rule to realize answer extraction. 基于互联网的中文问题回答系统由问题处理、信息检索、答案抽取和答案判断组成,利用命名实体识别、语义依存关系和案例规则模板实现答案抽取。
The paper presents an unsupervised learning algorithm to learn answer pattern for answer extraction module of Chinese Question Answering ( QA). 本文提出了一种基于无监督学习算法的问答模式抽取技术从互联网上抽取应用于汉语问答系统的答案模式。
In this paper, bank counseling is as example. It analyzes the structure and realization of bank counseling, and introduces question analyses, answer extraction, question sentence corpus construction, knowledge text tagging in details. 文章以银行业务咨询服务为例,分析了系统结构及实现过程,对问句分析、答案析取、问句语料库构建、文本知识标注等功能模块的实现进行了详细介绍。
A Question Answering contains question classification, query expansion, text retrieval, answer extraction and answer selection. Question classification and answer extraction are the most important. 问答系统包括问题分类、查询扩展、文本检索、答案抽取和答案选择排序,其中,问题分类和答案抽取最为关键。
The Open domain Question Answering system is composed of five parts, that is, question classification, question expansion, search engine, answer extraction and answer selection. 开放域问答系统通常包括问题分类、问题扩展、搜索引擎、答案抽取和答案选择五个主要部分。
This paper presents an answer extraction method based on the computation of sentence similarity between the question sentence and the candidate answer sentence. 我们提出了一种基于语句相似度计算的答案抽取方法,在此基础上实现了一个基于网络的中文问答系统。
Additionally, semantic Role Labeling of Chinese Question was tried to apply in Question Answering System for the Shan xi Tourism, which achieved good performance in question upstanding and answer extraction phase. 并探索性的将问句语义角色标注应用于面向山西旅游智能问答系统,在问题理解和答案抽取阶段取得了理想的实验效果。
Question analysis is the basic work of question-answering system. The effect of question analysis has an important influence on text retrieval and answer extraction in question-answering system. 问句分析是问答系统的基础工作,问句分析的效果对问答系统中的文本检索、答案抽取有重要的影响。
The key word from understanding stage need the information retrieval module to quickly find out in the document database of documents related to the answer extraction module. 对于问题理解阶段产生的关键词,信息检索模块要快速地在文档库找出相关的文档,交给答案抽取模块。
Question classification is an important part of question answering system; it provides the selecting strategy for answer extraction processing of the question answer system, so the classification accuracy directly influences the performance of the question answering system. 问句分类是问答系统的一个重要组成部分,它能为问答系统的答案抽取环节提供答案的选取策略,所以分类的准确性直接影响问答系统的性能。
The analysis for Question Answer ( QA) system shows that the relevance of documents as the source of answer extraction is the main factor which restricts the QA performance. 对目前问答系统的性能分析表明,用于答案抽取来源的文档的相关性是制约问答系统性能的主要因素。
In By means of the analyzing and studying to the understanding, information retrieval and answer extraction modules, the author put forward their own understanding and the answer extraction algorithm, designed and implemented a web-based Chinese Question-Answering System. 本文通过对问题理解、信息检索和答案抽取这三个主要模块的研究,提出了自己的问题理解和答案抽取算法,设计并实现了一个基于网络的中文自动问答系统。
This paper, base on open domain question answering system, focuses on the research of question classification, fact questions answer extraction and definition question answer extraction. 本文基于开放域问答系统,重点研究了问题理解的问题分类技术以及事实性问题和定义性问题的答案抽取技术。
The system of this study is composed of four modules: local data source construction, question processing, information searching and answer extraction. 系统由四个模块组成:本地数据源构建、问句处理、信息检索和答案抽取。
The English answer extraction is the most important core technology in Cross-Language Question Answering, and it is also the most critical steps for deciding the effectiveness and precision of the system. 英文答案的抽取是跨语言问答系统中最为重要的核心技术,也是决定系统效用以及精确度最关键的步骤。
The experiment shows that the method can improve the answer extraction accuracy. 实验证明,这种方法能够提高答案抽取的精度。
The system consists of four modules, the question analysis module, the information retrieval module, the answer extraction module and the FAQ module. 该系统包含四个模块,问题理解模块、信息检索模块、答案抽取模块以及FAQ模块。
Experiment result shows great efficiency. Secondly, this paper applies semantic role analysis techniques combines with question key-words on answer extraction towards factoid questions. 实验结果表明该分类模型具有良好的效果。2.针对事实性问题,本文利用语义角色分析和问句关键词相结合的方法进行答案抽取,用基于问句关键词的方法弥补语义角色分析的缺陷。
The system mainly contains three parts: question analyzing module, answer database generation module and answer extraction module. 系统包括三个主要组成部分:问句分析模块、答案数据库生成模块和答案抽取模块。
In Chapter 4, we carefully studied the Answer Extraction and Generation problems. 本文的第四章对问答系统中难度最大的一部分答案抽取和生成进行了研究。
Relevant document retrieval is a main component in QA system, and the relevance of its searching results with the question will directly affect the effectiveness of the answer extraction. 相关文档检索作为问答系统的一个重要组成部分,其检索结果与问题的相关性将直接影响答案抽取的效果。
QA system is a comprehensive use of natural language processing technology. Generally, the main part of a QA system includes question processing, information retrieval and answer extraction. 问答系统是自然语言处理技术的综合运用,可以把它分为问题处理,信息检索和答案抽取三个部分。