数学专业英语辅助写作系统

发布时间：2019-01-01 20:04

【摘要】：近年来,随着我国数学学科的蓬勃发展,广大数学工作者和青年学生在国际知名数学期刊上发表的论文数大幅提高,中国数学学科也成为了国际数学界不容忽视的一股力量。但与此同时,我国数学从业者的专业英语写作水平却还有很多不足,这也在一定程度上制约了中国数学学科的发展。一套简单易用的数学专业英语辅助写作系统能够帮助广大数学工作者尤其是青年学生提高专业英语写作水平,进而改善论文发表的成功率和时效。本文的主要工作就是这方面的一个尝试,系统核心是一个基于中英对照权威数学语料的搜索引擎。首先,本文通过对汉英数学书籍和文献的收集、整理、扫描和转换等操作,得到文本格式的原始语料。再通过符号和公式识别算法,解决了原始语料中的文本分段、乱码处理等问题。进一步,本文综合运用自然语言处理工具对段落文本断句,判别句对齐,使双语句对有序的保存到语料库中。其次,由于中文分词的准确性直接影响搜索结果的精确性,故将中文分词性能的提升作为本论文的研究重点。本文基于Jieba中文分词系统,结合数学论文特点,给出了中文分词的改进策略,提高了分词的效果。最后,基于搜索引擎技术完成数学写作辅助系统的搭建。实验表明,本文的系统达到设计功能,能够帮助作者在一定程度上提高数学专业英语写作水平。
[Abstract]:In recent years, with the vigorous development of mathematics in our country, the number of papers published by the vast number of mathematics workers and young students in internationally famous mathematics journals has greatly increased, and Chinese mathematics has become a force that can not be ignored in the international mathematics field. But at the same time, there are still many deficiencies in the professional English writing of mathematics practitioners in China, which restricts the development of Chinese mathematics to some extent. A set of simple and easy-to-use English aided writing system for mathematics specialty can help many mathematics workers, especially young students, to improve their professional English writing level, and then to improve the success rate and timeliness of publication. The main work of this paper is an attempt in this field. The core of the system is a search engine based on Chinese and English authoritative mathematical corpus. First of all, the original corpus of text format is obtained by collecting, sorting, scanning and converting Chinese and English mathematics books and documents. Then, the problems of text segmentation and random code processing in the original corpus are solved by the algorithm of symbol and formula recognition. Furthermore, this paper synthetically applies natural language processing tools to break sentences in paragraph texts and align discriminant sentences so that the pairs of double sentences can be stored in the corpus in an orderly manner. Secondly, the accuracy of Chinese word segmentation directly affects the accuracy of search results, so the improvement of Chinese word segmentation performance is the focus of this paper. Based on the Jieba Chinese word segmentation system and the characteristics of mathematical papers, this paper presents an improved strategy for Chinese word segmentation, which improves the effect of word segmentation. Finally, based on search engine technology to complete the construction of mathematical writing assistance system. The experiment shows that the system achieves the design function and can help the author to improve the writing level of mathematics major English to a certain extent.
【学位授予单位】：吉林大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP391.3

【相似文献】