摘要
在总结长期实践经验的基础上 ,笔者分析了为什么自然语言处理是一个相当困难的研究领域 ,而汉语信息处理是更加困难的研究领域。面对日益强烈的社会需求 ,汉语信息处理的研究方兴未艾。笔者探讨了开展这项研究的技术路线 。
Based on their long experience in the field of natural language processing (NLP), the authors are to explain why research in this domain is a very difficult one, and why, in addition, Chinese information processing (CIP) an even more difficult undertaking. With the development of the information society, there is an increasing need for the research on CIP, which has been unfolding in recent years. The authors also discuss the methodology of CIP, with a special emphasis on the importance of language knowledge base.
出处
《语言文字应用》
CSSCI
北大核心
2002年第2期51-58,共8页
Applied Linguistics
基金
国家自然基金6 94 830 0 3
973项目G19980 30 5 0 7- 4
86 3项目2001AA114 0 4 0
北大985
关键词
自然语言处理
汉语信息处理
语言知识库
natural language processing
Chinese information processing
language knowledge base