摘要
从特定领域的科技文献中发现新词,不断地丰富词表,以保证词表的容量是信息检索的一个很重要的基础工作.介绍了专业术语新词自动发现技术中术语提取及词表丰富工作中采取的关键步骤:英文标题串的规范化、标题串中专业术语新词的提取、确定新词对应的概念.最后,文中对实验结果进行了统计和比较,解释了统计结果中出现的一些现象,并得出了结论.
The discovery of new terminology in scientific literatures in special domain and the continuous enriching of vocabulary to maintain vocabulary scale is of crucial importance to information retrieval. In this paper, key steps of term extraction and vocabulary riching of the automatic discovery technology is introduced, which consists of the standardization of English title string, the extraction of new terminology from title string and the determination of concepts of new terminology. Finally, interpretation of statistical results are made through statistics and comparative study of the experiment and conclusions are reached.
出处
《哈尔滨师范大学自然科学学报》
CAS
2013年第5期49-52,共4页
Natural Science Journal of Harbin Normal University
基金
青年科技研究基金计划项目"庆阳红色旅游仿真实训综合平台的研发"的研究成果之一(QJ201301)
关键词
新词发现
词表丰富
形式化
专业术语新词
New word discovery
Riching vocabulary
Formalization
New terminology
