基于反馈规则学习的医学文献主题自动标引系统

An Automatic Subject Indexing System Based on Feedback Rule Learning

该文就中医药文献的自动标引研究,提出并开发了一个基于规则学习的主题自动标引系统。该系统从文献的题名中抽取并识别主题模式,相当有效地解决了医学科技文献的自动标引中涉及主/副题词的组配问题,并避免了基于词频处理的自动标引中存在的中文分词的障碍。开发完成的自动标引系统初期版本在大量中医药文献中进行了实验,取得了很好的结果,具备一定的实用性。

This paper provides a system using feedback rule-based learning method of automatic indexing(FRBLAI )for medical literature.The system has a relatively high performance in subject indexing problem,which involves the procedure of combination of Medical Headings and subheadings.Furthermore,FRBLAI avoids the main obstacle of word segmentation in Chinese information processing.Also the paper has a detailed description of the architecture of the indexing system.And finally,it gives an automatic indexing experiment in medical literature,which shows FRBLAI is a promising system for automatic indexing.