基于实体类百科知识的问句自动生成系统

  • 格式:pdf
  • 大小:1.32 MB
  • 文档页数:60

-I-
哈尔滨工业大学工学硕士学位论文
Abstract
There is too much information in the internet as the amount of users gets a high speed of increment. Many people get use to finding solutions of problems which they meet not only in job but also in daily life by using the search engine. If they are not trained how to use a search engine effectively or they do not know how to search information in the internet, it will cost them a lot of time to find what they want or select the goals from varieties of files. The interactive question answering system is designed to solve the problems described before. By importing some nature language processing technologies, the question answering system can understand what the user are looking for and return an answer to the user after processing on the question. Question generation is able to help the question answering system in the field of supplying the pairs of questions and their answers when the question answering system is lack of communications in that field. The field can be either specific or general. The technology of generating questions automatically in English has achieved a high level while the research in Chinese area is rare which has been part of question answering system, dialogue system and tutoring system. This research is aimed at adding pairs of question and answering to the database which is part of the knowledge system. We want to achieve that goal by automatically generating questions from a given text. The paper will show how we generate questions automatically in the followings. 1. The way to generate Chinese questions automatically by computers. Nowadays, the system of question generation can not deal with a whole sentence like human beings do. The preprocessing of a sentence is necessary for every question generation system. Our system is designed in a distributed way such that the functions of information processing can be done by several parts to speed the system up. The preprocessing part is divided into two main classes which consist of seven kinds of materials. We design an algorithm which combines the syntactic information and pattern matching to generate wh-questions. 2. The automatic classification of generated questions. The generated question will be classified into six categories due to the named entities recognized from a Chines sentence and the pattern. The questions are who questions, what time questions, where questions, what organization questions, what questions and why questions. 3. System evaluation and improving There are a serial of evaluation standards for English system which can be borrowed to value our system. At the same time, we invited some user to test our system and give their opinions for the system. We will improve our system based on these
Thesis for the Master Degree of Engineering
ENCYCLOPEDIC KNOWLEDGE BASED QUESTION AUTO-GENERATION SYSTEM
Candidate: Supervisor: Academic Degree Applied for: Specialty: Affiliation: Date of Defence: Degree-Conferring-Institution:
Lei You Prof. Xiaolong Wang Master of Engineering Computer Science and Technology Shenzhen Graduate School June, 2012 Harbin Institute of Technology
-
哈尔滨工业大学工学硕士学位论文
硕士学位论文
基于实体类百科知识的问句自动生成系统
ENCYCLOPEDIC KNOWLEDGE BASED QUESTION AUTO-GENERATION SYSTEM
尤磊
哈尔滨工业大学 2012 年 6 月
-
国内图书分类号: TP 391.3 国际图书分类号: 621.3
学校代码:10213 密级:公开


摘 要 ...................................................................................................................... I ABSTRACT ................................................................................................................. II 第 1 章 绪论 ........................................................................................................ 1 1.1 课题背景以及研究的目的和意义 ................................................................. 1 1.1.1 课题背景................................................................................................ 1 1.1.2 课题研究的目的和意义.......................................................................... 1 1.2 问句生成的研究现状 .................................................................................... 2 1.2.1 国外问句生成研究现状.......................................................................... 2 1.2.2 国内问句自动生成的研究现状 .............................................................. 4 1.2.3 国内外对话交流系统的研究现状 .......................................................... 4 1.3 本课题的主要研究内容 ................................................................................ 6 1.3.1 中文问句相关信息获取.......................................................................... 6 1.3.2 确定生成问句的种类 ............................................................................. 6 1.3.3 问句生成与评测 ..................................................................................... 6 1.4 本文结构安排............................................................................................... 7 第 2 章 基于问题自动生成相关的方法概述............................................................ 8 2.1 2.2 2.3 2.4 引言 .............................................................................................................. 8 中文分词系统及算法 ................................................................................... 8 基于命名实体识别信息的算法 .................................................................... 9 基于依存句法信息的算法 .......................................................................... 11