论文部分内容阅读
在对 725万字的信息领域专业文献中带英文注释的术语（汉英术语）进行了人工标记，然后利用程序提取汉英术语及其前界环境（前至少 4个汉字）的工作基础上 ,本文对汉英术语的自身特征和前界环境进行了分析，目的是为术语的自动抽取提供规则及相关统计数据。
Based on the work of 725 words of terminology (English terminology) with English annotation in professional literature of information field, and then using the program to extract the terminology of Chinese-English terms and their frontier environment (at least 4 Chinese characters) The author analyzes the self-characteristics of Chinese-English terms and the frontier environment, and aims to provide rules and relevant statistical data for the automatic extraction of terms.