| 最近几年来，在说话信息处置的研究和开辟中，机械翻译的感化日趋突显出来。机械翻译是若何应用盘算机来停止分歧说话之间的翻译。机械翻译研究的症结在于人类对天然说话表达机制的整体熟悉和运用盘算机完成说话翻译的可操作性。开辟汉韩机械翻译体系的重要目标是为了人们更好地停止汉语和韩语的交换。建交12年来，韩国和中国在经济上文明上的互相关系与任何一个国度比拟都加倍深挚。1990年仅为26。5亿美元的韩中商业额客岁到达了580亿美元。假如在收集交换傍边没有遭到任何说话上的妨碍，能够会扩展韩中两国之间的交换。本文在第一章概述了机械翻译的概念，研究配景，汗青及办法，经由过程对机械翻译汗青的回想，指出该研究范畴的最新结果和成长趋向；在第二章平略论了汉韩转换生成的难点；在第三章中评论辩论了本体系的基本语法实际和剖析算法，包含汉韩机械翻译体系的设计思惟、常识库的组织和体系的完成等等。本体系采取的情势语法系统是基于合一语法，剖析算法采取的是Tomita算法，韩语论文网站，Tomita算法与LR 算法比拟比拟合适剖析天然说话，韩语毕业论文，能以较高效力获得一切能够的剖析成果 ；第四章中从几个方面评论辩论了汉韩句法剖析及转换生成的战略；在第五章中重要描写本汉韩机械翻译体系的运转的进程。在上述任务基本上，第六章给出需停止的进一步研究本体系在Window2000操作体系上采取Visual C//6。0作为开辟对象，运用MicroSoft Access6。0数据库治理体系来治理常识库。今朝本体系的常识库有汉韩双语辞书和剖析转换规矩库，个中辞书中有350多个词，规矩库中有125条。本体系可以或许根本地处置韩国语中的如今时态、曩昔时态、未来时态的陈说句，对动词的尊重词、动词、描述词的派生变更。 Abstract: In recent years, the research and development of information disposal talk, machine translation effect increasingly prominent. Mechanical translation is how to use the computer to stop speaking translation differences. Machine translation research is the crux of the whole mankind on the expression of natural language mechanism familiar with computer to complete the translation operation to speak. Open up an important goal of Chinese and Korean machine translation system in order to better stop is the exchange of Chinese and korean. Over the past 12 years, the economic civilization in the mutual relations between South Korea and China and any countries are more deep. Only 26 in 1990. The $500 million China trade last year reached $58 billion. If the collection was not prejudice any talk among the exchange on the exchange between Korea and China will expand. The in the machine translation of the first chapter is an overview of the concept, research background, history and way, through the process of mechanical translation history memories. It is pointed out that the research field of the latest results and development trend; in the second chapter flat analyzed the difficulties of Chinese and Korean transformational generative; in chapter three comments argued the system of basic grammar and parsing algorithm, contains Chinese and Korean machine translation system design ideas, knowledge base organization and system to complete. The system uses the situation grammar system is based on unification grammar and parsing algorithm adopted is Tomita algorithm, Tomita and LR algorithms compare match suitable analysis of natural language, with high efficiency to obtain all possible results of the analysis; in the fourth chapter, from a few comments debate on the Chinese and Korean syntactic analysis and transformational generative strategy; in chapter five important description of the process of the operation of the Chinese and Korean machine translation system. In the above task basically, the sixth chapter is the need for further discussion of this stop system in Window2000 operating system by Visual C//6. 0 as a development tool, using MicroSoft Access6. 0 database management system to manage the knowledge base. The current system of knowledge base and Korean Chinese bilingual dictionaries and analysis and conversion rules library and medium dictionaries has more than 350 words, rule library has 125. The system can root of the disposal of the local Korean in the present tense, past tense, future tense, "said Chen, sentence, to the verb respect words, verbs, describe change of word derive. 目录: 中文摘要 2-3 ABSTRACT 3 目录 5-8 第一章 引言 8-31 1.1 机器翻译的基本概念 8 1.2 机器翻译的探讨背景 8-11 1.2.1 语言学理论与计算机技术的结合更加深入 8-10 1.2.2 语料库措施和统计措施的复兴 10-11 1.2.3 大规模语言资源与测试平台的运用 11 1.3 机器翻译的探讨历史 11-17 1.3.1 萌芽期 11-13 1.3.2 草创期 13-14 1.3.3 复苏期 14-16 1.3.4 繁荣期 16-17 1.4 机器翻译的趋势及未来 17-20 1.4.1 网上翻译的运用 17-18 1.4.2 未来需要的自动翻译技术 18-20 1.5 机器翻译的基本探讨措施 20-25 1.5.1 直接翻译法(第一代机器翻译系统) 21 1.5.2 基于转换的措施 21-22 1.5.3 基于中间语言的措施 22 1.5.4 统计措施 22-24 1.5.5 基于实例措施 24-25 1.6 机器翻译系统的开发情况 25-31 1.6.1 典型的机器翻译系统 25-28 1.6.2 中国机器翻译近况 28-29 1.6.3 韩国开发的机器翻译系统 29 1.6.4 基于规则的机器翻译系统开发情况 29-31 第二章 汉韩转换生成的难点探讨 31-45 2.1 汉韩机器翻译的难点略论 31-34 2.1.1 汉语语法略论的难点 31-32 2.1.2 汉语到韩语转换的难点 32-34 2.2 汉语与韩语的对比和比较 34-45 2.2.1 略论语的特点 34-35 2.2.2 粘着语的特点 35 2.2.3 汉语语序的特点 35-36 2.2.4 时态变化 36-38 2.2.5 词类比较 38-41 2.2.6 词性标注的比较 41-45 第三章 汉韩机器翻译系统的探讨与开发 45-60 3.1 汉韩机器翻译系统的开发环境 45 3.2 汉韩机器翻译系统的总体结构与算法 45-56 3.2.1 总体翻译过程 45-46 3.2.2 复杂特征集和合一算法 46-48 3.2.3 格语法 48-50 3.2.4 句法略论- Tomita 算法 50-56 3.3 汉韩机器翻译系统的工作流程 56 3.4 汉韩语言知识库结构的主要思想 56-60 3.4.1 汉韩电子词典系统 56-57 3.4.2 汉韩语言知识规则库 57-60 第四章 汉语句法略论及转换生成 60-70 4.1 汉语句法略论 60-62 4.1.1 句法略论流程 60 4.1.2 Tomita略论算法 60-62 4.2 转换生成 62-70 4.2.1 转换生成过程 62 4.2.2 转换器的构成 62-66 4.2.3 生成器构成 66-67 4.2.4 生成算法 67-70 第五章 汉韩机器翻译系统的运行 70-77 5.1 汉韩机器翻译系统的设计思想 70 5.2 汉韩机器翻译系统的界面和功能 70-75 5.3 汉韩机器翻译系统的测试结果 75-77 第六章 总论 77-80 6.1 本探讨的总结 77-78 6.2 未来机器翻译的需要 78-80 参考文献 80-82 致谢、声明 82-83 附录 83-96 个人简历、在学期间的探讨成果及发表的学术论文 96 |
